mirror of
https://github.com/MLSysBook/TinyTorch.git
synced 2026-05-10 16:38:39 -05:00
92781736a1
Major changes: - Moved TinyGPT from Module 16 to examples/tinygpt (capstone demo) - Fixed Module 10 (optimizers) and Module 11 (training) bugs - All 16 modules now passing tests (100% health) - Added comprehensive testing with 'tito test --comprehensive' - Renamed example files for clarity (train_xor_network.py, etc.) - Created working TinyGPT example structure - Updated documentation to reflect 15 core modules + examples - Added KISS principle and testing framework documentation
1 line
97 KiB
JavaScript
1 line
97 KiB
JavaScript
Search.setIndex({"alltitles": {"1. Build First": [[25, "build-first"]], "1. Cognitive Load Reduction": [[19, "cognitive-load-reduction"]], "1. Module-Level Testing": [[21, "module-level-testing"]], "1. Single Responsibility Components": [[19, "single-responsibility-components"]], "16 Individual Test Files": [[16, "individual-test-files"]], "2. Debugging Clarity": [[19, "debugging-clarity"]], "2. Integration Testing": [[21, "integration-testing"]], "2. Minimal Interfaces": [[19, "minimal-interfaces"]], "2. Use Immediately": [[25, "use-immediately"]], "3. Checkpoint Testing": [[21, "checkpoint-testing"]], "3. Explicit Over Implicit": [[19, "explicit-over-implicit"]], "3. Modification Confidence": [[19, "modification-confidence"]], "3. Understand Systems": [[25, "understand-systems"]], "4. Example Validation": [[21, "example-validation"]], "4. Reflect on Trade-offs": [[25, "reflect-on-trade-offs"]], "A/B Testing and Experimentation": [[14, "a-b-testing-and-experimentation"]], "Academic Progress Markers": [[16, "academic-progress-markers"]], "Academic Recognition": [[22, "academic-recognition"]], "Acknowledgments": [[18, "acknowledgments"]], "Activation Layer Integration": [[3, "activation-layer-integration"]], "Advanced Configuration": [[17, "advanced-configuration"]], "Advanced Monitoring and Observability": [[14, "advanced-monitoring-and-observability"]], "Advanced Network Analysis": [[4, "advanced-network-analysis"]], "After Architecture": [[16, "after-architecture"]], "After Foundation": [[16, "after-foundation"]], "After Inference": [[16, "after-inference"]], "After Language Models": [[16, "after-language-models"]], "After Training": [[16, "after-training"]], "Agent Team Implementation": [[16, "agent-team-implementation"]], "Attention Masking": [[6, "attention-masking"]], "Attention Mechanisms": [[15, "attention-mechanisms"]], "Attention vs Convolution": [[6, "attention-vs-convolution"]], "Auto-Grading Process": [[17, "auto-grading-process"]], "Automated Grading": [[22, "automated-grading"]], "Automated Module Completion": [[16, "automated-module-completion"]], "Automatic Differentiation System": [[8, "automatic-differentiation-system"]], "Automatic Differentiation Theory": [[8, "automatic-differentiation-theory"]], "Automatic Module-to-Checkpoint Mapping": [[16, "automatic-module-to-checkpoint-mapping"]], "Batch Operations": [[17, "batch-operations"]], "Before Adding Complexity": [[19, "before-adding-complexity"]], "Before Commits": [[21, "before-commits"]], "Benchmarking Best Practices": [[13, "benchmarking-best-practices"]], "Best Practices": [[17, "best-practices"], [21, "best-practices"]], "Beyond Algorithms: System-Level Understanding": [[25, "beyond-algorithms-system-level-understanding"]], "Build Up: Chapter 4 - Layers": [[23, "build-up-chapter-4-layers"]], "Build \u2192 Use \u2192 Understand": [[24, "build-use-understand"]], "Building Blocks": [[18, null]], "Building Blocks (Modules 03-07)": [[22, "building-blocks-modules-03-07"]], "Built-in CIFAR-10 Download and Loading": [[7, "built-in-cifar-10-download-and-loading"]], "CLI Commands": [[16, "cli-commands"]], "CNN Architecture Patterns": [[5, "cnn-architecture-patterns"]], "CNN Building Blocks": [[5, "cnn-building-blocks"]], "Capability Statements": [[16, "capability-statements"]], "Capability-Driven Learning Journey": [[16, "capability-driven-learning-journey"]], "Capstone Project Validation": [[14, "capstone-project-validation"]], "Career Impact": [[25, "career-impact"]], "Career Transformation:": [[25, "career-transformation"]], "Check Your Progress": [[16, "check-your-progress"]], "Choose Your Module": [[24, "choose-your-module"]], "Classroom Use Overview": [[22, null]], "Clear Learning Goals": [[16, "clear-learning-goals"]], "Code Review Checklist": [[19, "code-review-checklist"]], "Code Style": [[19, "code-style"]], "Collecting Student Submissions": [[17, "collecting-student-submissions"]], "Common Issues": [[17, "common-issues"]], "Community": [[22, "community"]], "Complete CNN Architecture": [[5, "complete-cnn-architecture"]], "Complete Course Infrastructure": [[22, "complete-course-infrastructure"]], "Complete Data Pipeline System": [[7, "complete-data-pipeline-system"]], "Complete Instructor Documentation": [[22, null]], "Complete Model Lifecycle Management": [[14, "complete-model-lifecycle-management"]], "Complete Training Integration": [[9, "complete-training-integration"]], "Complete Training Pipeline": [[10, "complete-training-pipeline"]], "Complete Training with Checkpointing": [[10, "complete-training-with-checkpointing"]], "Components Implemented": [[15, "components-implemented"]], "Comprehensive Compression Pipeline": [[11, "comprehensive-compression-pipeline"]], "Comprehensive Curriculum": [[22, "comprehensive-curriculum"]], "Comprehensive Performance Reporter": [[13, "comprehensive-performance-reporter"]], "Comprehensive Test Suite": [[0, "comprehensive-test-suite"], [2, "comprehensive-test-suite"], [3, "comprehensive-test-suite"], [4, "comprehensive-test-suite"], [5, "comprehensive-test-suite"], [7, "comprehensive-test-suite"], [8, "comprehensive-test-suite"], [9, "comprehensive-test-suite"], [10, "comprehensive-test-suite"], [11, "comprehensive-test-suite"], [12, "comprehensive-test-suite"], [13, "comprehensive-test-suite"], [14, "comprehensive-test-suite"]], "Comprehensive Testing with TinyTorch": [[21, "comprehensive-testing-with-tinytorch"]], "Compression Techniques": [[11, "compression-techniques"]], "Computational Graph Construction": [[8, "computational-graph-construction"]], "Computer Vision Fundamentals": [[5, "computer-vision-fundamentals"]], "Continuous Learning Systems": [[14, "continuous-learning-systems"]], "Continuous Learning and Automation": [[14, "continuous-learning-and-automation"]], "Convolution Mathematics": [[5, "convolution-mathematics"]], "Convolution Operation Details": [[5, "convolution-operation-details"]], "Core Activation Functions": [[2, "core-activation-functions"]], "Core Convolution Implementation": [[5, "core-convolution-implementation"]], "Core Functions": [[0, "core-functions"]], "Core Language Processing": [[15, "core-language-processing"]], "Core Layer Implementation": [[3, "core-layer-implementation"]], "Core Optimization Algorithms": [[9, "core-optimization-algorithms"]], "Core Programming Patterns": [[0, "core-programming-patterns"]], "Core Tensor Class": [[1, "core-tensor-class"]], "Course Module Overview": [[22, "course-module-overview"]], "Course Planning Recommendations": [[17, "course-planning-recommendations"]], "Creating Student Assignments": [[17, "creating-student-assignments"]], "Data Engineering Principles": [[7, "data-engineering-principles"]], "Data Preprocessing Pipeline": [[7, "data-preprocessing-pipeline"]], "Dataset Abstraction System": [[7, "dataset-abstraction-system"]], "Deep Learning Foundations": [[20, "deep-learning-foundations"]], "Dense Layer Implementation": [[3, "dense-layer-implementation"]], "Design Patterns and Best Practices": [[4, "design-patterns-and-best-practices"]], "Developer Profile Class": [[0, "developer-profile-class"]], "Development Workflow": [[0, "development-workflow"], [1, "development-workflow"], [2, "development-workflow"], [3, "development-workflow"], [4, "development-workflow"], [5, "development-workflow"], [7, "development-workflow"], [8, "development-workflow"], [9, "development-workflow"], [10, "development-workflow"], [11, "development-workflow"], [12, "development-workflow"], [13, "development-workflow"], [14, "development-workflow"], [24, "development-workflow"]], "Documentation": [[22, "documentation"]], "Documentation of Trade-offs": [[19, "documentation-of-trade-offs"]], "During Development": [[21, "during-development"]], "Educational Benefits": [[19, "educational-benefits"]], "Educational Philosophy": [[15, "educational-philosophy"]], "Educational Value": [[21, "educational-value"]], "Efficient Data Loading System": [[7, "efficient-data-loading-system"]], "End-of-Semester Workflow": [[17, "end-of-semester-workflow"]], "Enterprise Integration and Governance": [[14, "enterprise-integration-and-governance"]], "Essential Daily Commands": [[17, "essential-daily-commands"]], "Essential Operations": [[1, "essential-operations"]], "Evaluation Methodology": [[13, "evaluation-methodology"]], "Evaluation Metrics System": [[10, "evaluation-metrics-system"]], "Example: Activation Functions": [[18, "example-activation-functions"]], "Exporting Grades": [[17, "exporting-grades"]], "File Organization": [[19, "file-organization"]], "Flexible Point Distribution": [[22, "flexible-point-distribution"]], "Foundation": [[18, null]], "Foundation (Modules 00-02)": [[22, "foundation-modules-00-02"]], "Foundation (Weeks 1-2)": [[24, "foundation-weeks-1-2"]], "Framework Deep Dives": [[20, "framework-deep-dives"]], "Framework Generalization": [[18, null]], "Function Composition Theory": [[4, "function-composition-theory"]], "Generating Student Feedback": [[17, "generating-student-feedback"]], "Get Help": [[24, "get-help"]], "Getting Started as an Instructor": [[22, "getting-started-as-an-instructor"]], "Hardware Performance Fundamentals": [[12, "hardware-performance-fundamentals"]], "Hardware-Optimized Core Operations": [[12, "hardware-optimized-core-operations"]], "Health Status": [[21, "health-status"]], "Immediate Feedback": [[24, "immediate-feedback"]], "Implementation & Theory": [[20, "implementation-theory"]], "Implementation Patterns": [[3, "implementation-patterns"], [8, "implementation-patterns"]], "Important Limitations": [[23, "important-limitations"]], "Industry Feedback": [[22, "industry-feedback"]], "Industry Preparation": [[22, "industry-preparation"]], "Inline Testing": [[0, "inline-testing"], [1, "inline-testing"]], "Inline Testing & Compression Analysis": [[11, "inline-testing-compression-analysis"]], "Inline Testing & Convergence Analysis": [[9, "inline-testing-convergence-analysis"]], "Inline Testing & Development": [[3, "inline-testing-development"]], "Inline Testing & Evaluation Validation": [[13, "inline-testing-evaluation-validation"]], "Inline Testing & Mathematical Verification": [[8, "inline-testing-mathematical-verification"]], "Inline Testing & Performance Analysis": [[12, "inline-testing-performance-analysis"]], "Inline Testing & Production Validation": [[14, "inline-testing-production-validation"]], "Inline Testing & Real Data Validation": [[7, "inline-testing-real-data-validation"]], "Inline Testing & Training Analysis": [[10, "inline-testing-training-analysis"]], "Inline Testing & Visualization": [[2, "inline-testing-visualization"], [4, "inline-testing-visualization"], [5, "inline-testing-visualization"]], "Instructor Resources": [[22, "instructor-resources"]], "Instructor-Friendly Features": [[22, "instructor-friendly-features"]], "Integration with Development": [[16, "integration-with-development"]], "KISS Design Decisions": [[19, "kiss-design-decisions"]], "KISS Guidelines for Contributors": [[19, "kiss-guidelines-for-contributors"]], "KISS Principle in Testing": [[21, "kiss-principle-in-testing"]], "KISS Principle in TinyTorch": [[19, null]], "KISS in Practice": [[19, "kiss-in-practice"]], "KISS vs. Performance": [[19, "kiss-vs-performance"]], "Keep It Simple, Stupid": [[19, "keep-it-simple-stupid"]], "Key Insights": [[15, "key-insights"]], "Knowledge Distillation for Compact Models": [[11, "knowledge-distillation-for-compact-models"]], "Language Models (Module 16)": [[22, "language-models-module-16"]], "Launch Immediately (0 Setup Required)": [[23, "launch-immediately-0-setup-required"]], "Learning Objectives": [[15, "learning-objectives"]], "Learning Outcomes: Becoming an ML Systems Engineer": [[25, "learning-outcomes-becoming-an-ml-systems-engineer"]], "Learning Path (Progressive Complexity)": [[24, "learning-path-progressive-complexity"]], "Learning Philosophy: Build, Use, Reflect": [[18, "learning-philosophy-build-use-reflect"]], "Learning Rate Scheduling Systems": [[9, "learning-rate-scheduling-systems"]], "Loss Function Library": [[10, "loss-function-library"]], "MLOps Architecture Patterns": [[14, "mlops-architecture-patterns"]], "MLPerf-Inspired Benchmarking Framework": [[13, "mlperf-inspired-benchmarking-framework"]], "Machine Learning Engineering": [[10, "machine-learning-engineering"]], "Machine Learning Systems": [[20, "machine-learning-systems"]], "Manual Testing Examples": [[2, "manual-testing-examples"], [3, "manual-testing-examples"], [4, "manual-testing-examples"], [5, "manual-testing-examples"], [7, "manual-testing-examples"], [8, "manual-testing-examples"], [9, "manual-testing-examples"], [10, "manual-testing-examples"], [11, "manual-testing-examples"], [12, "manual-testing-examples"], [13, "manual-testing-examples"]], "Manual Verification": [[1, "manual-verification"]], "Mathematical Foundations": [[3, "mathematical-foundations"], [8, "mathematical-foundations"], [9, "mathematical-foundations"]], "Mathematical Properties Comparison": [[2, "mathematical-properties-comparison"]], "Memory and Performance": [[1, "memory-and-performance"]], "Mid-Semester Status Check": [[17, "mid-semester-status-check"]], "Minimal Frameworks": [[20, "minimal-frameworks"]], "Model Compression Analysis System": [[11, "model-compression-analysis-system"]], "Module 16: TinyGPT - Language Models": [[15, null]], "Module Completion Workflow": [[16, "module-completion-workflow"]], "Module Design": [[19, "module-design"]], "Module Status Indicators": [[21, "module-status-indicators"]], "Module Tests": [[1, "module-tests"]], "Module: Activations": [[2, null]], "Module: Attention": [[6, null]], "Module: Autograd": [[8, null]], "Module: Benchmarking": [[13, null]], "Module: CNN": [[5, null]], "Module: Compression": [[11, null]], "Module: DataLoader": [[7, null]], "Module: Kernels": [[12, null]], "Module: Layers": [[3, null]], "Module: MLOps": [[14, null]], "Module: Networks": [[4, null]], "Module: Optimizers": [[9, null]], "Module: Setup": [[0, null]], "Module: Tensor": [[1, null]], "Module: Training": [[10, null]], "Monitoring Assignment Status": [[17, "monitoring-assignment-status"]], "Neural Network Building Blocks": [[3, "neural-network-building-blocks"]], "Neural Network Integration": [[8, "neural-network-integration"]], "Next Steps": [[23, "next-steps"]], "Numerical Stability Considerations": [[2, "numerical-stability-considerations"]], "Optimization Algorithm Implementations": [[9, "optimization-algorithm-implementations"]], "Optimization Techniques": [[12, "optimization-techniques"]], "Optimization Theory": [[9, "optimization-theory"]], "Pedagogical Excellence": [[22, "pedagogical-excellence"]], "Pedagogical Philosophy: Build \u2192 Use \u2192 Understand": [[25, "pedagogical-philosophy-build-use-understand"]], "Perfect For:": [[25, "perfect-for"]], "Performance Characteristics": [[9, "performance-characteristics"]], "Performance Engineering Methodology": [[12, "performance-engineering-methodology"]], "Performance Profiling Framework": [[12, "performance-profiling-framework"]], "Performance and Gradient Properties": [[2, "performance-and-gradient-properties"]], "Prerequisites": [[0, "prerequisites"], [2, "prerequisites"], [3, "prerequisites"], [4, "prerequisites"], [5, "prerequisites"], [7, "prerequisites"], [8, "prerequisites"], [9, "prerequisites"], [10, "prerequisites"], [11, "prerequisites"], [12, "prerequisites"], [13, "prerequisites"], [14, "prerequisites"], [15, "prerequisites"]], "Prerequisites Check": [[1, "prerequisites-check"]], "Production & Performance (Weeks 7-8)": [[24, "production-performance-weeks-7-8"]], "Production (Modules 12-15)": [[22, "production-modules-12-15"]], "Production Deployment Considerations": [[11, "production-deployment-considerations"]], "Production ML Engineering": [[14, "production-ml-engineering"]], "Production ML Pipeline Patterns": [[7, "production-ml-pipeline-patterns"]], "Production Serving Infrastructure": [[14, "production-serving-infrastructure"]], "Production Systems": [[18, null]], "Professional Reporting": [[13, "professional-reporting"]], "Professional Skills": [[25, "professional-skills"]], "Progressive Testing Pattern": [[21, "progressive-testing-pattern"]], "Project-Based Assessment": [[22, "project-based-assessment"]], "Proven Learning Outcomes": [[22, "proven-learning-outcomes"]], "Proven Student Outcomes": [[24, "proven-student-outcomes"]], "Pruning Systems for Model Sparsity": [[11, "pruning-systems-for-model-sparsity"]], "Quality Assurance": [[24, "quality-assurance"]], "Quantization for Memory Efficiency": [[11, "quantization-for-memory-efficiency"]], "Quantized Operation Optimization": [[12, "quantized-operation-optimization"]], "Quick Exploration Path": [[23, null]], "Quick Start (3 Steps)": [[22, "quick-start-3-steps"]], "Quick Start (5 minutes)": [[24, "quick-start-5-minutes"]], "Quick Start: Run All Tests": [[21, "quick-start-run-all-tests"]], "Quick Taste: Try Module 1 Right Now": [[18, "quick-taste-try-module-1-right-now"]], "ReLU (Rectified Linear Unit)": [[2, "relu-rectified-linear-unit"]], "Ready to Become an ML Systems Engineer?": [[25, "ready-to-become-an-ml-systems-engineer"]], "Ready to Start?": [[18, "ready-to-start"], [24, "ready-to-start"]], "Real Capability Validation": [[16, "real-capability-validation"]], "Real Data, Real Systems": [[24, "real-data-real-systems"]], "Real Results": [[24, null]], "Real-World Applications": [[0, "real-world-applications"], [2, "real-world-applications"], [3, "real-world-applications"], [4, "real-world-applications"], [5, "real-world-applications"], [6, "real-world-applications"], [7, "real-world-applications"], [8, "real-world-applications"], [9, "real-world-applications"], [10, "real-world-applications"], [11, "real-world-applications"], [12, "real-world-applications"], [13, "real-world-applications"], [14, "real-world-applications"]], "Real-World Connections": [[1, "real-world-connections"]], "Real-World Evaluation Scenarios": [[13, "real-world-evaluation-scenarios"]], "Real-World Relevance": [[16, "real-world-relevance"]], "Real-World Training Workflows": [[10, "real-world-training-workflows"]], "Recommended Exploration Path": [[23, "recommended-exploration-path"]], "Refactoring Triggers": [[19, "refactoring-triggers"]], "Releasing Assignments to Students": [[17, "releasing-assignments-to-students"]], "Rich CLI Integration": [[16, "rich-cli-integration"]], "Rich Progress Tracking": [[16, "rich-progress-tracking"]], "Rich Visual Feedback": [[16, "rich-visual-feedback"]], "Rich Visual Timeline": [[16, "rich-visual-timeline"]], "SIMD Vectorized Operations": [[12, "simd-vectorized-operations"]], "Scaled Dot-Product Attention": [[6, "scaled-dot-product-attention"]], "Self-Attention Wrapper": [[6, "self-attention-wrapper"]], "Sequential Network Architecture": [[4, "sequential-network-architecture"]], "Serious Development Path": [[24, null]], "Sigmoid Activation": [[2, "sigmoid-activation"]], "Specialized Network Builders": [[4, "specialized-network-builders"]], "Start Here: Chapter 1 - Setup": [[23, "start-here-chapter-1-setup"]], "Statistical Validation System": [[13, "statistical-validation-system"]], "Step 1: Clone and Setup Repository": [[17, "step-1-clone-and-setup-repository"]], "Step 1: Get the Code": [[24, "step-1-get-the-code"]], "Step 2: Setup Environment": [[24, "step-2-setup-environment"]], "Step 2: Verify Installation": [[17, "step-2-verify-installation"]], "Step 3: Initialize NBGrader Environment": [[17, "step-3-initialize-nbgrader-environment"]], "Step 3: Start Building": [[24, "step-3-start-building"]], "Step 4: Build \u2192 Test \u2192 Export \u2192 Use": [[24, "step-4-build-test-export-use"]], "Step 4: Verify Complete Setup": [[17, "step-4-verify-complete-setup"]], "Step-by-Step Implementation": [[1, "step-by-step-implementation"]], "Student Success Metrics": [[22, "student-success-metrics"]], "Student Testimonials": [[22, "student-testimonials"]], "Success Stories: What Students Say": [[25, "success-stories-what-students-say"]], "Support Tools": [[22, "support-tools"]], "System Information Class": [[0, "system-information-class"]], "System Maintenance": [[17, "system-maintenance"]], "Systems & Engineering": [[20, "systems-engineering"]], "Systems Engineering Patterns": [[11, "systems-engineering-patterns"]], "Systems Integration Patterns": [[10, "systems-integration-patterns"]], "Systems Performance Considerations": [[7, "systems-performance-considerations"]], "Systems Thinking": [[21, "systems-thinking"]], "Systems Thinking Over Task Completion": [[16, "systems-thinking-over-task-completion"]], "Systems Understanding": [[25, "systems-understanding"]], "Tanh (Hyperbolic Tangent)": [[2, "tanh-hyperbolic-tangent"]], "Target Audience: Future ML Systems Engineers": [[25, "target-audience-future-ml-systems-engineers"]], "Technical Mastery": [[25, "technical-mastery"]], "Tensors as Universal Data Structures": [[1, "tensors-as-universal-data-structures"]], "Test Architecture": [[21, "test-architecture"]], "Test Capabilities": [[16, "test-capabilities"]], "Test Coverage (20 Tests)": [[0, "test-coverage-20-tests"]], "Test Coverage Areas": [[2, "test-coverage-areas"], [3, "test-coverage-areas"], [4, "test-coverage-areas"], [5, "test-coverage-areas"], [7, "test-coverage-areas"], [8, "test-coverage-areas"], [9, "test-coverage-areas"], [10, "test-coverage-areas"], [11, "test-coverage-areas"], [12, "test-coverage-areas"], [13, "test-coverage-areas"], [14, "test-coverage-areas"]], "Test Files Organization": [[21, "test-files-organization"]], "Test Results Interpretation": [[21, "test-results-interpretation"]], "Testing Framework": [[21, null]], "Testing Levels": [[21, "testing-levels"]], "Testing Philosophy": [[21, "testing-philosophy"]], "The Attention Formula Explained": [[6, "the-attention-formula-explained"]], "The Core Difference": [[18, "the-core-difference"]], "The KISS Promise": [[19, "the-kiss-promise"]], "The Perfect Learning Combination": [[18, null]], "The Problem We\u2019re Solving": [[25, "the-problem-were-solving"]], "The TinyTorch Difference:": [[25, "the-tinytorch-difference"]], "The TinyTorch Vision": [[25, null]], "The Trade-off": [[19, "the-trade-off"]], "The tito CLI System": [[24, "the-tito-cli-system"]], "Then Try: Chapter 3 - Activations": [[23, "then-try-chapter-3-activations"]], "Time Estimate": [[15, "time-estimate"]], "TinyTorch Foundation": [[0, "tinytorch-foundation"]], "TinyTorch: Build Your Own ML Framework from First Principles": [[18, null]], "TinyTorch: Clarity by Design": [[19, "tinytorch-clarity-by-design"]], "Traditional ML Education:": [[25, "traditional-ml-education"]], "Traditional ML Frameworks: Complexity by Default": [[19, "traditional-ml-frameworks-complexity-by-default"]], "Training Infrastructure": [[15, "training-infrastructure"]], "Training System Architecture": [[10, "training-system-architecture"]], "Training Systems": [[18, null]], "Training Systems (Modules 08-11)": [[22, "training-systems-modules-08-11"]], "Training Systems (Weeks 5-6)": [[24, "training-systems-weeks-5-6"]], "Transformer Architecture": [[15, "transformer-architecture"]], "Troubleshooting Failed Tests": [[21, "troubleshooting-failed-tests"]], "Understanding the TinyTorch Module Structure": [[17, "understanding-the-tinytorch-module-structure"]], "Unique Value Proposition": [[25, "unique-value-proposition"]], "University Adoption": [[22, "university-adoption"]], "Visual Timeline": [[16, "visual-timeline"]], "Visualization and Analysis": [[4, "visualization-and-analysis"]], "Weekly Assignment Routine": [[17, "weekly-assignment-routine"]], "What Makes This Special": [[15, "what-makes-this-special"]], "What Makes TinyTorch Different:": [[25, "what-makes-tinytorch-different"]], "What We Teach: Systems Thinking": [[25, "what-we-teach-systems-thinking"]], "What You\u2019ll Build": [[18, null], [24, "what-youll-build"]], "What You\u2019ll Experience": [[23, null]], "What You\u2019ll Understand": [[23, "what-youll-understand"]], "What to Tell Your Students": [[17, "what-to-tell-your-students"]], "What\u2019s New in This Module": [[7, "whats-new-in-this-module"], [10, "whats-new-in-this-module"]], "When We Optimize": [[19, "when-we-optimize"]], "Why Attention Revolutionized AI": [[6, "why-attention-revolutionized-ai"]], "Why Choose TinyTorch for Teaching?": [[22, "why-choose-tinytorch-for-teaching"]], "Why KISS Matters in ML Education": [[19, "why-kiss-matters-in-ml-education"]], "Why Tensors Matter in ML": [[1, "why-tensors-matter-in-ml"]], "Why This Approach Works": [[24, "why-this-approach-works"]], "\ud83c\udf1f Success Stories": [[22, "success-stories"]], "\ud83c\udf89 Ready to Build?": [[0, "ready-to-build"], [1, "ready-to-build"], [2, "ready-to-build"], [3, "ready-to-build"], [4, "ready-to-build"], [5, "ready-to-build"], [7, "ready-to-build"], [8, "ready-to-build"], [9, "ready-to-build"], [10, "ready-to-build"], [11, "ready-to-build"], [12, "ready-to-build"], [13, "ready-to-build"], [14, "ready-to-build"]], "\ud83c\udf89 Success Metrics": [[17, "success-metrics"]], "\ud83c\udf93 Academic Courses": [[20, "academic-courses"]], "\ud83c\udf93 Phase 2: Course Preparation": [[17, "phase-2-course-preparation"]], "\ud83c\udfaf Foundation": [[16, "foundation"]], "\ud83c\udfaf How It All Connects": [[18, null]], "\ud83c\udfaf Inference Deployment": [[16, "inference-deployment"]], "\ud83c\udfaf Key Concepts": [[0, "key-concepts"], [1, "key-concepts"], [2, "key-concepts"], [3, "key-concepts"], [4, "key-concepts"], [5, "key-concepts"], [7, "key-concepts"], [8, "key-concepts"], [9, "key-concepts"], [10, "key-concepts"], [11, "key-concepts"], [12, "key-concepts"], [13, "key-concepts"], [14, "key-concepts"]], "\ud83c\udfaf Learning Objectives": [[0, "learning-objectives"], [1, "learning-objectives"], [2, "learning-objectives"], [3, "learning-objectives"], [4, "learning-objectives"], [5, "learning-objectives"], [6, "learning-objectives"], [7, "learning-objectives"], [8, "learning-objectives"], [9, "learning-objectives"], [10, "learning-objectives"], [11, "learning-objectives"], [12, "learning-objectives"], [13, "learning-objectives"], [14, "learning-objectives"]], "\ud83c\udfaf NEW: CIFAR-10 Support for North Star Goal": [[7, "new-cifar-10-support-for-north-star-goal"]], "\ud83c\udfaf NEW: Model Checkpointing & Evaluation Tools": [[10, "new-model-checkpointing-evaluation-tools"]], "\ud83c\udfaf Neural Architecture": [[16, "neural-architecture"]], "\ud83c\udfaf Perfect For:": [[18, "perfect-for"]], "\ud83c\udfaf Quick Reference Commands": [[17, "quick-reference-commands"]], "\ud83c\udfaf Success Criteria": [[6, "success-criteria"]], "\ud83c\udfaf The Complete Instructor Journey": [[17, "the-complete-instructor-journey"]], "\ud83c\udfaf TinyTorch Checkpoint System": [[16, null]], "\ud83c\udfaf Training": [[16, "training"]], "\ud83c\udfd7\ufe0f Implementation Architecture": [[16, "implementation-architecture"]], "\ud83c\udfed Production Internals": [[20, "production-internals"]], "\ud83d\udc65 Who This Is For": [[18, "who-this-is-for"]], "\ud83d\udc68\u200d\ud83c\udfeb Instructor Guide: NBGrader + TinyTorch": [[17, null]], "\ud83d\udcbe Save Your Progress": [[0, null], [1, null], [2, null], [3, null], [4, null], [5, null], [6, null], [7, null], [8, null], [9, null], [10, null], [11, null], [12, null], [13, null], [14, null], [15, null]], "\ud83d\udcc8 Learning Outcomes by Checkpoint": [[16, "learning-outcomes-by-checkpoint"]], "\ud83d\udcc8 Module Progression": [[6, "module-progression"]], "\ud83d\udcca Module Info": [[0, "module-info"], [1, "module-info"], [2, "module-info"], [3, "module-info"], [4, "module-info"], [5, "module-info"], [6, "module-info"], [7, "module-info"], [8, "module-info"], [9, "module-info"], [10, "module-info"], [11, "module-info"], [12, "module-info"], [13, "module-info"], [14, "module-info"]], "\ud83d\udcca Phase 4: Grading Workflow": [[17, "phase-4-grading-workflow"]], "\ud83d\udcca Tracking Your Progress": [[16, "tracking-your-progress"]], "\ud83d\udccb Assessment Options": [[22, "assessment-options"]], "\ud83d\udccb Prerequisites": [[17, "prerequisites"]], "\ud83d\udcd6 Recommended Books": [[20, "recommended-books"]], "\ud83d\udcda Additional Learning Resources": [[20, null]], "\ud83d\udcda Course Journey: 16 Modules - Foundation to Framework": [[18, "course-journey-16-modules-foundation-to-framework"]], "\ud83d\udcda Phase 7: Student Guidance": [[17, "phase-7-student-guidance"]], "\ud83d\udcda Prerequisites:": [[18, "prerequisites"]], "\ud83d\udcda What You\u2019ll Build": [[0, "what-youll-build"], [1, "what-youll-build"], [2, "what-youll-build"], [3, "what-youll-build"], [4, "what-youll-build"], [5, "what-youll-build"], [6, "what-youll-build"], [7, "what-youll-build"], [8, "what-youll-build"], [9, "what-youll-build"], [10, "what-youll-build"], [11, "what-youll-build"], [12, "what-youll-build"], [13, "what-youll-build"], [14, "what-youll-build"]], "\ud83d\udcdd Phase 3: Assignment Management": [[17, "phase-3-assignment-management"]], "\ud83d\udcde Getting Help": [[17, "getting-help"]], "\ud83d\udcde Next Steps": [[22, "next-steps"]], "\ud83d\udd17 Complete System Integration": [[18, "complete-system-integration"]], "\ud83d\udd25 Language Models": [[16, "language-models"]], "\ud83d\udd27 Phase 5: Common Workflows": [[17, "phase-5-common-workflows"]], "\ud83d\udd2c Key Concepts": [[6, "key-concepts"]], "\ud83d\ude80 Career Impact:": [[18, "career-impact"]], "\ud83d\ude80 From Attention to Modern AI": [[6, "from-attention-to-modern-ai"]], "\ud83d\ude80 Getting Started": [[0, "getting-started"], [1, "getting-started"], [2, "getting-started"], [3, "getting-started"], [4, "getting-started"], [5, "getting-started"], [7, "getting-started"], [8, "getting-started"], [9, "getting-started"], [10, "getting-started"], [11, "getting-started"], [12, "getting-started"], [13, "getting-started"], [14, "getting-started"]], "\ud83d\ude80 Phase 1: Initial Setup (One-Time)": [[17, "phase-1-initial-setup-one-time"]], "\ud83d\ude80 The Five Major Checkpoints": [[16, "the-five-major-checkpoints"]], "\ud83d\ude80 Your Journey Starts Here": [[16, "your-journey-starts-here"]], "\ud83d\udee0\ufe0f Alternative Implementations": [[20, "alternative-implementations"]], "\ud83d\udee0\ufe0f Phase 6: Troubleshooting & Tips": [[17, "phase-6-troubleshooting-tips"]], "\ud83d\udee0\ufe0f Using the Checkpoint System": [[16, "using-the-checkpoint-system"]], "\ud83e\udde0 Build \u2192 Use \u2192 Analyze": [[2, "build-use-analyze"], [5, "build-use-analyze"], [8, "build-use-analyze"], [13, "build-use-analyze"]], "\ud83e\udde0 Build \u2192 Use \u2192 Deploy": [[14, "build-use-deploy"]], "\ud83e\udde0 Build \u2192 Use \u2192 Optimize": [[4, "build-use-optimize"], [7, "build-use-optimize"], [9, "build-use-optimize"], [10, "build-use-optimize"], [11, "build-use-optimize"], [12, "build-use-optimize"]], "\ud83e\udde0 Build \u2192 Use \u2192 Reflect": [[0, "build-use-reflect"], [3, "build-use-reflect"]], "\ud83e\udde0 Build \u2192 Use \u2192 Understand": [[1, "build-use-understand"], [6, "build-use-understand"]], "\ud83e\udde0 Why This Approach Works": [[16, "why-this-approach-works"]], "\ud83e\uddea Testing Your Implementation": [[0, "testing-your-implementation"], [1, "testing-your-implementation"], [2, "testing-your-implementation"], [3, "testing-your-implementation"], [4, "testing-your-implementation"], [5, "testing-your-implementation"], [7, "testing-your-implementation"], [8, "testing-your-implementation"], [9, "testing-your-implementation"], [10, "testing-your-implementation"], [11, "testing-your-implementation"], [12, "testing-your-implementation"], [13, "testing-your-implementation"], [14, "testing-your-implementation"]], "\ud83e\uddf1 Building Blocks (Weeks 3-4)": [[24, "building-blocks-weeks-3-4"]]}, "docnames": ["chapters/01-setup", "chapters/02-tensor", "chapters/03-activations", "chapters/04-layers", "chapters/05-dense", "chapters/06-spatial", "chapters/07-attention", "chapters/08-dataloader", "chapters/09-autograd", "chapters/10-optimizers", "chapters/11-training", "chapters/12-compression", "chapters/13-kernels", "chapters/14-benchmarking", "chapters/15-mlops", "chapters/16-tinygpt", "checkpoint-system", "instructor-guide", "intro", "kiss-principle", "resources", "testing-framework", "usage-paths/classroom-use", "usage-paths/quick-exploration", "usage-paths/serious-development", "vision"], "envversion": {"sphinx": 62, "sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.intersphinx": 1, "sphinxcontrib.bibtex": 9}, "filenames": ["chapters/01-setup.md", "chapters/02-tensor.md", "chapters/03-activations.md", "chapters/04-layers.md", "chapters/05-dense.md", "chapters/06-spatial.md", "chapters/07-attention.md", "chapters/08-dataloader.md", "chapters/09-autograd.md", "chapters/10-optimizers.md", "chapters/11-training.md", "chapters/12-compression.md", "chapters/13-kernels.md", "chapters/14-benchmarking.md", "chapters/15-mlops.md", "chapters/16-tinygpt.md", "checkpoint-system.md", "instructor-guide.md", "intro.md", "kiss-principle.md", "resources.md", "testing-framework.md", "usage-paths/classroom-use.md", "usage-paths/quick-exploration.md", "usage-paths/serious-development.md", "vision.md"], "indexentries": {}, "objects": {}, "objnames": {}, "objtypes": {}, "terms": {"": [0, 2, 3, 4, 5, 6, 8, 9, 11, 12, 13, 14, 15, 17, 18, 19, 22, 25], "0": [1, 2, 3, 4, 6, 7, 8, 9, 10, 11, 12, 13, 14, 16, 17, 18, 19, 21, 22], "00": [16, 17, 21], "000": 7, "001": [9, 10, 19], "00_introduct": 17, "01": [9, 10, 12, 13, 14, 16, 17, 21, 22, 24], "01_setup": [0, 16, 17, 22, 24], "02": [14, 17, 24], "02_tensor": [1, 16, 17], "03": [17, 24], "03_activ": [2, 16, 17], "04": [17, 22, 24], "04_layer": [3, 16, 17], "05": [14, 22, 24], "05_dens": [4, 16, 17], "05_network": 4, "06": [22, 24], "06_cnn": 5, "06_spatial": [5, 16, 17], "07": [17, 24], "07_attent": [6, 16, 17], "07_dataload": 7, "08": [17, 24], "08_autograd": 8, "08_dataload": [7, 16, 17], "09": [22, 24], "09_autograd": [8, 16, 17], "09_optim": 9, "0f": 13, "1": [0, 1, 2, 3, 4, 5, 6, 8, 9, 10, 11, 12, 13, 14, 15], "10": [1, 3, 4, 5, 8, 9, 10, 11, 12, 13, 14, 16, 17, 18, 21, 22, 24, 25], "100": [4, 9, 10, 12, 13, 14, 16, 18, 19, 20, 21, 24, 25], "1000": [10, 12, 13, 14], "10_optim": [9, 16, 17], "10_train": 10, "10mb": 11, "10x": 19, "11": [5, 12, 15, 17, 18, 24], "11_compress": 11, "11_train": [10, 16, 17], "12": [0, 1, 2, 5, 13, 17, 18, 24], "123": 10, "128": [3, 4, 5, 9, 10, 11, 13, 18], "12_compress": [11, 16, 17], "12_kernel": 12, "13": [4, 5, 10, 14, 17, 18, 22, 24], "13_benchmark": 13, "13_kernel": [12, 16, 17], "14": [0, 5, 13, 14, 17, 18, 22], "14_benchmark": [13, 16, 17], "14_mlop": 14, "15": [1, 5, 16, 17, 18, 21], "15_mlop": [14, 16, 17], "16": [5, 7, 8, 10, 17, 24, 25], "16_capston": 17, "16_tinygpt": [15, 16], "17": [5, 17], "170mb": 7, "18": 5, "19": 5, "1d": 5, "1e": [12, 19], "1e9": 6, "1f": [11, 12], "1x": 12, "2": [0, 1, 2, 3, 4, 5, 6, 8, 9, 10, 11, 12, 14, 18, 23], "20": [5, 9, 10, 23], "200": [22, 24], "21": 5, "22": 5, "224n": 20, "23": [5, 14], "231n": 20, "234": 10, "24": 5, "249r": 20, "25": [5, 11], "256": 4, "27": 2, "278": 10, "28x28": 4, "2d": 5, "2f": [7, 11, 12, 13, 14], "2px": [], "2x": 8, "2y": 8, "3": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 16, 18], "30": [5, 10, 13, 14, 17, 22, 25], "300": 17, "32": [4, 5, 7, 10, 11], "329": 20, "32x32": 7, "33": 16, "333": [], "345": 10, "37": 8, "3d": 1, "3px": [], "3x": 12, "3y\u00b2": 8, "4": [1, 2, 3, 4, 5, 6, 8, 10, 11, 12, 13, 15, 18, 19], "40": [12, 25], "456": 10, "45b7d1": [], "4d": 1, "4ecdc4": [], "4f": [9, 10, 11, 14], "4x": [11, 12], "5": [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 18, 19, 23], "50": [7, 9, 10, 11, 13, 14], "500": [12, 14], "523": 10, "543": 10, "55": 18, "567": 10, "5mb": 11, "6": [1, 4, 5, 7, 8, 9, 11, 13, 15, 18, 20], "60": [], "64": [4, 10, 11, 19], "66": 16, "6f": 9, "7": [4, 5, 7, 11, 14, 18], "70": [14, 15], "73": 2, "75": [7, 11, 16, 24], "76": 2, "784": [3, 4, 9, 10, 11, 13, 18, 25], "8": [1, 4, 5, 8, 9, 10, 11, 12, 13, 14, 17, 18, 19], "80": 22, "800": 12, "85": 22, "88": 2, "8x": 12, "9": [1, 4, 5, 7, 9, 17, 18, 19], "90": [21, 22, 25], "94": 14, "95": [13, 16, 17, 18, 21, 22, 24, 25], "96": 2, "96ceb4": [], "999": [9, 19], "99th": 13, "A": [12, 13, 18, 24], "AND": [22, 24, 25], "By": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15], "For": [17, 19, 23], "If": 17, "No": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 18, 19, 23, 25], "Not": [16, 17, 18, 25], "ONE": 25, "OR": 1, "On": [17, 20], "One": [19, 22], "Or": 17, "The": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 15, 21, 23], "Then": 19, "These": [18, 20], "With": 3, "_": [7, 12], "__add__": [18, 19], "__call__": 10, "__getitem__": 7, "__init__": [3, 6, 12, 25], "__len__": 7, "__radd__": 19, "_apply_with_state_manag": 19, "_c": 19, "_nn": 19, "_relu_impl": 19, "a1": [], "a2": [], "a3": [], "a4": [], "a_b_test": 14, "a_int8": 12, "aaron": 20, "abil": [2, 23, 25], "abl": [0, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14], "about": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 18, 19, 23], "absolut": 11, "abstract": [1, 16, 17, 19, 22], "academ": [10, 13, 18], "acc_scor": 10, "acceler": [1, 9, 12, 13, 22], "access": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 17], "accordingli": 12, "account": 23, "accumul": [8, 9, 12, 18, 25], "accur": [11, 13, 14], "accuraci": [7, 10, 11, 12, 13, 14, 18, 25], "accuracy_drop": 14, "achiev": [6, 7, 9, 11, 12, 16, 18, 19, 25], "across": [1, 2, 5, 7, 10, 14, 15, 16, 24, 25], "action": [4, 17, 18, 21], "activ": [0, 1, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 19, 22, 24], "activations_dev": [2, 3, 4, 5, 10, 11, 13], "activationwithdropoutandnorm": 19, "actual": [6, 7, 11, 12, 13, 16, 18, 19, 20, 25], "acycl": 8, "ad": 8, "adam": [9, 10, 16, 17, 18, 22, 24, 25], "adam_upd": 19, "adapt": [6, 9, 14], "add": [3, 4, 5, 7, 8, 9, 11, 12, 13, 14, 15, 16, 17, 19, 22], "add_numb": 0, "add_vari": 14, "addit": [1, 3, 8, 10, 15], "additional_data": 14, "address": 12, "adjust": [9, 17], "admonit": 18, "advanc": [0, 5, 6, 7, 8, 9, 13, 16, 25], "adversari": 14, "affect": 25, "affili": 0, "after": [4, 6, 10, 11, 18, 19, 21, 23, 24, 25], "against": [9, 11], "aggress": 11, "ai": [4, 8, 9, 10, 11, 12, 14, 16, 20, 22, 23], "air": 14, "alert": 14, "alert_manag": 14, "alert_threshold": 14, "alertmanag": 14, "alexnet": [4, 5], "algebra": 18, "algorithm": [8, 11, 12, 14, 16, 18, 20], "align": 6, "aliv": 2, "all": [0, 1, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 16, 17, 22, 23, 24], "along": 1, "alpha": 11, "alwai": [17, 19], "am": 6, "amaz": 22, "an": 17, "analysi": [2, 3, 5, 8, 14, 16, 18, 25], "analyt": [9, 17], "analyz": [4, 7, 9, 10, 11], "analyze_network_behavior": 4, "analyze_result": 14, "analyze_weight_distribut": 11, "andrej": 20, "andrii": 20, "ani": [1, 2, 4, 6, 7, 16, 17, 18, 19, 22, 23, 25], "announc": 17, "answer": 25, "anyon": 18, "anyth": 23, "anytim": 18, "api": [18, 19, 23, 25], "app": 11, "append": 12, "appli": [0, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 20], "applic": [22, 25], "approach": [0, 10, 18, 19, 20, 23, 25], "appropri": [2, 4], "approve_for_product": 14, "approved_model": 14, "approxim": [3, 4], "ar": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 21, 22, 23], "architectur": [0, 2, 3, 6, 7, 11, 13, 18, 20, 22, 24, 25], "archiv": 17, "aren": 18, "arg": 12, "arithmet": [0, 1, 8, 12], "around": [8, 14], "arrai": [1, 12, 17, 18, 22, 24], "art": [0, 4, 6], "artifact": 14, "artifici": 3, "ascii": 0, "ask": [18, 19, 25], "aspect": 6, "assert": [1, 17], "assert_allclos": 12, "assess": 10, "assign": [16, 18, 22, 24], "assign_vari": 14, "assist": 5, "assumpt": 4, "assur": [11, 14], "astronaut": [], "astyp": 12, "attent": [2, 4, 16, 17, 18, 20, 22, 25], "attention_dev": 6, "attention_weight": 6, "attribut": 0, "audit": 14, "audit_log": 14, "augment": 7, "aur\u00e9lien": 20, "auto": 24, "auto_sc": 14, "autodiff": 8, "autograd": [9, 10, 14, 16, 17, 18, 20, 21, 22, 24, 25], "autograd_dev": [8, 9], "autom": [2, 10, 17, 18, 24], "automat": [3, 7, 10, 14, 17, 18, 22, 24, 25], "automated_model_improv": 14, "automlpipelin": 14, "autonom": [4, 5, 7, 11, 14], "autoregress": [15, 18, 24], "avail": [6, 14, 17], "avgpool": 5, "avoid": [13, 19], "awai": [24, 25], "awar": [12, 18, 21, 24, 25], "axi": 1, "b": [3, 8, 12, 13], "b_int8": 12, "backbon": [5, 7], "backpropag": [8, 10, 22, 24], "backward": [8, 9, 10, 11, 18, 19, 25], "balanc": [4, 7, 9, 11, 14], "bandwidth": 25, "bar": 16, "base": [3, 5, 7, 8, 9, 11, 13, 14, 15, 16], "base_model": 14, "baselin": [12, 13, 21], "baseline_model": 13, "baseline_op": 12, "baseline_result": [12, 13], "baseline_stat": 12, "baseline_tim": 12, "baseline_v1": 13, "basic": [0, 1, 2, 3, 5, 8, 9, 17, 18, 21, 22], "batch": [3, 4, 5, 7, 9, 10, 11, 12, 13, 15, 19, 22, 24, 25], "batch_data": [7, 12], "batch_i": 19, "batch_idx": 7, "batch_imag": 7, "batch_input": [9, 11], "batch_label": [7, 11], "batch_siz": [7, 10], "batch_target": 9, "batch_tim": 13, "batch_x": 19, "battery_constraint": 13, "bce_loss": 10, "beauti": 3, "becaus": 25, "becom": [8, 10, 18, 19, 23], "befor": [14, 17, 25], "begin": [1, 16, 17, 25], "beginn": 0, "behavior": [0, 2, 3, 4, 9, 10], "behind": [9, 16, 20], "benchmark": [10, 12, 14, 16, 18, 22, 24], "benchmark_report": 14, "benchmarking_dev": 13, "benefici": 2, "benefit": [11, 12], "bengio": 20, "bert": [6, 9], "best": [6, 9, 10, 18, 20, 25], "best_model": 10, "beta1": [9, 19], "beta2": [9, 19], "better": [3, 11, 19, 22, 24], "between": [3, 4, 7, 11, 12, 15, 18, 22, 23], "beyond": [8, 12, 18], "bia": [3, 8, 9, 13, 18, 19, 25], "bias": 4, "bias_testing_requir": 14, "bidirect": 6, "bidirection": 6, "bidirectional_mask": 6, "big": 14, "billion": 7, "bin": [0, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 17, 22, 24], "binari": [2, 3, 4, 7, 10], "binary_classifi": 4, "binary_label": 10, "binary_loss": 10, "binarycrossentropi": 10, "binarycrossentropyloss": 10, "binder": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 18, 23], "bla": 19, "black": [12, 22], "blob": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15], "block": [1, 4, 6, 8, 12, 14, 15, 16, 17, 23], "bonu": 22, "book": 18, "bookmark": [], "both": [0, 2, 12, 15, 16, 22, 24, 25], "bottleneck": [7, 12, 13, 16, 19, 25], "bound": 2, "box": [12, 22], "break": [7, 19], "breakthrough": [2, 4, 13], "bridg": [11, 12, 18, 22], "bring": [10, 16], "broadcast": [1, 25], "broader": 20, "brows": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15], "browser": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 18, 23], "bug": 24, "build": [15, 16, 17, 19, 20, 21], "builder": 25, "built": [4, 13, 14, 16, 18, 20, 23, 24, 25], "burkov": 20, "busi": [13, 14], "button": 23, "c": [8, 12, 17, 18, 20, 24], "c_float": 12, "c_int32": 12, "cach": [7, 12, 18, 25], "cache_friendly_matmul": 12, "calcul": [10, 11], "calculate_model_s": 11, "calculate_spars": 11, "call": [3, 7, 19, 25], "came": 25, "camera": 5, "can": [2, 3, 4, 6, 14, 16, 17, 18, 19, 22, 23, 25], "capabl": [4, 12, 14, 18, 21], "capston": [10, 18, 22], "captur": 15, "car": 4, "card": 22, "care": [2, 9, 13], "carefulli": 20, "case": [1, 2, 3, 6, 7, 8, 19], "caus": 2, "causal": 6, "causal_mask": 6, "causalmask": 15, "cd": [1, 14, 17, 22, 24], "ce_loss": 10, "celebr": 16, "cell": 17, "center": [2, 3, 12, 13], "central": 14, "certain": [18, 25], "chain": [3, 4, 8], "challeng": [14, 18, 20, 22, 25], "chang": [14, 21], "channel": [5, 11], "chapter": [18, 22], "charact": [15, 16, 18], "characterist": [2, 4, 5, 7, 8, 12], "chart": 13, "chartoken": 15, "chatgpt": 6, "check": [0, 14, 21, 24], "checkpoint": [18, 24, 25], "checkpoint_00_environ": 16, "checkpoint_01_found": 16, "checkpoint_02_intellig": 16, "checkpoint_03_compon": 16, "checkpoint_04_network": 16, "checkpoint_05_learn": 16, "checkpoint_06_attent": 16, "checkpoint_07_st": 16, "checkpoint_08_differenti": 16, "checkpoint_09_optim": 16, "checkpoint_10_train": 16, "checkpoint_11_regular": 16, "checkpoint_12_kernel": 16, "checkpoint_13_benchmark": 16, "checkpoint_14_deploy": 16, "checkpoint_15_capston": 16, "checkpoint_path": 10, "chemistri": 8, "chip": 20, "choic": [4, 5, 9, 13, 18, 25], "choos": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 18, 19, 25], "ci": [13, 14], "cifar": [10, 16, 17, 18, 21, 22, 24, 25], "cifar10": [7, 10, 13], "cifar10_v3": 14, "cifar10dataset": [7, 10], "circular": [], "claim": 13, "clariti": 15, "class": [3, 4, 5, 6, 7, 8, 10, 12, 18, 19, 23, 24, 25], "class_indic": 10, "classif": [2, 3, 4, 5, 10, 16, 23, 24], "classifi": [3, 4, 8, 24], "classification_loss": 10, "classroom": [18, 23, 25], "clean": [0, 17], "cleanup": 8, "clear": [0, 9, 17, 19, 21], "clearest": 19, "clearli": 13, "clearsolut": 17, "cli": [0, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 17, 18, 22, 25], "click": [18, 23], "clip": 6, "clone": [22, 24], "closer": 16, "cloud": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 25], "cnn": [2, 3, 4, 6, 7, 10, 14, 20, 24, 25], "cnn_dev": 5, "cnn_model": 10, "co": 12, "coco": 7, "code": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 21, 23, 25], "code_stub": 17, "coher": [6, 15], "cohes": [10, 25], "colab": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15], "collabor": 4, "collect": [0, 14], "color": [], "cols_a": 12, "cols_b": 12, "column": 12, "com": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 17, 22, 24], "combin": [3, 4, 9, 11, 22, 23], "come": [2, 14, 22], "comfort": 18, "command": 22, "commit": 23, "common": [1, 3, 4, 6, 10, 25], "commonli": 2, "commun": [13, 17], "compani": [7, 10, 22], "companion": [18, 20], "compar": [2, 4, 5, 9, 12, 13, 18, 25], "compare_model": [13, 14], "compare_network": 4, "compare_oper": 12, "comparison": [4, 12, 13, 14], "compat": [0, 2], "compil": 12, "complement": 20, "complet": [0, 1, 2, 3, 4, 6, 8, 11, 12, 13, 15, 19, 20, 21, 23, 24, 25], "complex": [2, 3, 4, 7, 8, 9, 16, 21, 25], "complex_funct": 8, "complianc": 14, "compliance_approv": 14, "compliance_track": 14, "compon": [0, 3, 6, 8, 10, 14, 16, 18, 21, 22, 23, 24, 25], "compos": [3, 4, 5], "composit": [3, 8, 19, 24], "comprehens": [16, 17, 18, 20, 24], "compress": [4, 10, 12, 13, 14, 16, 18, 20, 22, 24], "compress_for_mobile_deploy": 11, "compress_model": 13, "compressed_model": [13, 14], "compressed_s": 11, "compression_appli": 14, "compression_dev": 11, "compression_optim": 14, "compression_ratio": [11, 13], "compressionmetr": 11, "comput": [0, 1, 2, 3, 4, 6, 7, 9, 10, 11, 12, 13, 14, 15, 16, 17, 20, 22, 24, 25], "compute_confusion_matrix": 10, "compute_loss": 7, "concept": [15, 18, 19, 25], "concern": 19, "conclus": 13, "concret": [7, 16], "concurr": 14, "concurrent_us": 13, "condit": 13, "confid": [13, 14, 22], "confidence_interv": 13, "confidence_level": 13, "config": 14, "configur": [0, 7, 10, 13, 14, 16, 23], "configure_alert": 14, "configure_enterprise_featur": 14, "configure_mobile_scenario": 13, "configure_polici": 14, "configure_server_scenario": 13, "configure_stag": 14, "configure_statistical_paramet": 14, "confirm": [2, 3, 16, 21], "confus": [10, 19], "confusion_matrix": 10, "congratul": 14, "connect": [2, 4, 5, 6, 8, 14, 15, 16, 17, 22, 25], "consider": [10, 24, 25], "consist": [3, 4, 5, 7, 13, 14, 17, 24], "constrain": 20, "constraint": [7, 9, 11, 12, 14, 25], "construct": 16, "constructor": 1, "consult": 17, "consum": 18, "consumpt": 13, "contact": [0, 22, 24], "contain": 19, "contemporari": 6, "content": [0, 6], "context": [6, 15, 18, 20, 25], "continu": [4, 7, 9, 10, 24], "continuous_learn": 14, "continuous_target": 10, "continuouslearn": 14, "contribut": 16, "contributor": 0, "control": [2, 4, 6, 8, 13, 14, 17], "conv": [5, 19], "conv2d": [5, 10, 19], "conv2d_advanc": 19, "conv2d_optim": 19, "conv2d_simpl": 19, "conv2d_vector": 19, "conv_lay": 5, "conveni": 6, "converg": [10, 18, 24, 25], "convers": 11, "conversion_r": 14, "convert": [5, 17], "convex": 9, "convolut": [4, 16, 17, 18, 19, 20, 22, 24, 25], "coordin": [10, 16], "copi": [1, 17], "core": [4, 6, 7, 8, 10, 13, 14, 16, 19, 21, 24], "correct": [0, 2, 3, 4, 7, 8, 9, 10, 11, 12, 13, 22, 24], "correctli": [2, 3, 4, 5, 8, 9, 10, 11, 13, 14, 16, 21], "correl": 5, "correspond": 20, "corrupt": 7, "cost": [11, 25], "could": 25, "count": [4, 5, 11], "count_paramet": 11, "cours": [0, 14], "course_archive_fall2024": 17, "coursework": 16, "courvil": 20, "cover": [7, 17], "coverag": 24, "cpu": 12, "cpu_usag": 14, "craft": 5, "creat": [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 22, 23, 24, 25], "create_bidirectional_mask": 6, "create_causal_mask": 6, "create_classification_network": 4, "create_compact_model": 11, "create_data_pipelin": 7, "create_dependency_graph_visu": [], "create_learning_roadmap": [], "create_mlp": 4, "create_padding_mask": 6, "create_presentation_slid": 13, "create_regression_network": 4, "create_system_architecture_diagram": [], "creation": [4, 7, 8, 23], "criterion": 9, "critic": [2, 7, 9, 11, 14, 25], "cross": [5, 15, 21, 24], "crossentropi": 10, "crossentropyloss": 10, "crucial": [9, 23], "cs249r": 18, "csv": [13, 17], "ct": 5, "cudnn": 12, "culmin": 10, "cumul": 16, "curiou": 18, "current": [16, 17], "current_epoch": 10, "current_production_model": 14, "curriculum": [], "curv": 10, "custom": [0, 10, 12, 17, 18, 20, 22, 24, 25], "custom_scor": 10, "custommetr": 10, "cut": 25, "cycl": [0, 18, 25], "czf": 17, "d": 8, "d_k": 6, "d_model": 6, "dai": [14, 18, 25], "daili": 0, "dall": 6, "dashboard": 22, "data": [2, 3, 4, 5, 6, 8, 9, 10, 12, 13, 14, 16, 17, 18, 19, 20, 22, 23, 25], "data_collector": 14, "data_freshness_threshold": 14, "data_lineage_track": 14, "data_valid": 14, "databas": 17, "dataload": [9, 10, 14, 16, 18, 22, 24], "dataloader_dev": [7, 10], "dataset": [1, 10, 13, 16, 18, 19, 22, 24, 25], "dataset_path": 7, "date": 17, "db": 17, "debug": [2, 3, 10, 13, 17, 18, 25], "decai": 9, "decis": [4, 10, 25], "decreas": [5, 11], "dedic": 21, "deep": [2, 3, 4, 5, 8, 9, 18, 19, 24, 25], "deep_net": 4, "deeper": 5, "deepli": [22, 24], "def": [6, 7, 8, 9, 10, 11, 12, 14, 18, 19, 25], "default": 0, "defin": [3, 10], "degrad": 12, "demand": [11, 14], "demonstr": [14, 15, 18, 21, 25], "dens": [4, 5, 8, 9, 10, 11, 13, 15, 16, 18, 22, 23, 24], "dense_dev": 4, "depend": [5, 6, 7, 8, 9, 11, 12, 13, 14, 17, 21, 24], "dependency_graph": [], "deploi": [0, 16, 24, 25], "deploy": [0, 10, 13, 14, 17, 18, 20, 22, 24, 25], "deploy_candid": 14, "deploy_complete_system": 14, "deploy_model": 14, "deployment_approv": 14, "depth": [4, 6], "dequant": 11, "deriv": 8, "descent": [9, 24], "design": [0, 3, 5, 7, 9, 10, 11, 12, 13, 14, 16, 18, 20, 25], "destroi": 25, "detail": [16, 17, 19, 22, 25], "detect": [0, 5, 12, 14, 21], "detection_method": 14, "detector": 5, "determin": 14, "dev": 24, "develop": [6, 15, 17, 18, 22, 23, 25], "developerprofil": 0, "devic": [10, 11, 19], "df": 8, "diagnosi": 5, "diagnost": [5, 10], "diagram": [], "differ": [1, 2, 3, 4, 5, 6, 7, 8, 11, 13, 15, 20], "differenti": [10, 14, 16, 17, 18, 22, 24, 25], "difficulti": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14], "digit": 4, "dilat": 19, "dimens": [1, 3, 4, 5], "dimension": [1, 4, 5, 14, 16, 17, 18, 22, 24], "direct": [0, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 16, 17, 24], "directli": [1, 6, 16, 22], "directori": 17, "disast": 14, "discov": [], "discuss": [22, 24], "disk": 7, "displai": 13, "distillation_loss": 11, "distillationloss": 11, "distract": 19, "distribut": [2, 7, 10, 11, 14, 17, 18, 25], "dive": [], "divis": [1, 8], "do": [18, 19, 21, 25], "doctor": [0, 17, 21, 24], "document": [0, 13, 16, 17, 20, 25], "doe": [16, 18, 19, 25], "doesn": 9, "dollar": 7, "domain": [4, 15, 25], "don": 22, "done": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 21], "dot": 12, "download": [0, 1, 2, 3, 4, 5, 6, 8, 9, 10, 11, 12, 13, 14, 15, 17], "download_cifar10": 7, "downsampl": 5, "dramat": 5, "drift": 14, "drift_detector": 14, "drift_scor": 14, "driftdetector": 14, "drive": [0, 4, 5, 14], "driven": [12, 14, 25], "drop_last": 7, "dtype": [1, 19], "dual": 8, "due": 17, "durat": 22, "dure": [0, 3, 7, 9, 10, 17, 25], "dx": 8, "dy": [2, 8], "dynam": [3, 6, 8, 9, 10, 24], "e": [2, 6, 16], "each": [2, 4, 5, 8, 9, 16, 17, 18, 19, 21, 22], "earli": [5, 21], "early_stopping_pati": 10, "easi": [3, 10, 19], "easier": [15, 19], "ecosystem": 14, "edg": [1, 2, 3, 5, 7, 8, 10, 11, 13, 19, 20, 25], "edit": [0, 1], "educ": [0, 2, 3, 4, 5, 18, 20, 23], "edward": 20, "effect": [9, 13, 18, 19, 25], "effici": [1, 3, 5, 8, 9, 12, 17, 20, 24, 25], "efficientnet": 5, "element": [1, 2], "els": [13, 16, 18], "embed": [3, 15], "embedding_drift": 14, "embodi": 21, "emploi": 12, "empow": 19, "enabl": [2, 3, 5, 6, 7, 8, 9, 10, 15, 16, 18, 19, 24], "encod": [4, 6, 15], "encount": 17, "encourag": 17, "encryption_at_rest": 14, "encryption_in_transit": 14, "end": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 20, 22, 23, 24], "endpoint": 14, "endpoint_url": 14, "energi": [11, 13], "enforc": 13, "engag": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 18], "engin": [0, 1, 3, 8, 13, 16, 17, 18, 19, 22, 24], "enhanc": 16, "enjoi": [0, 1, 2, 3, 5, 7, 8, 9, 10, 11, 12, 13, 14], "ensur": [0, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 16, 17, 21, 22, 24], "entir": [0, 1, 4, 8, 10, 11, 14], "entrepreneurship": 25, "entropi": 15, "enumer": 7, "environ": [0, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 16, 18, 20, 21, 22, 23], "epoch": [9, 10, 14], "equal": 8, "equat": 9, "error": [0, 1, 3, 7, 10, 17, 21, 24], "error_r": 14, "especi": [12, 13, 15], "essenti": [10, 12, 15, 19, 21, 22], "establish": [0, 13, 19, 20], "estim": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14], "estimated_tim": [], "etc": [1, 8, 19], "etl": 7, "evalu": [14, 17, 18, 22, 24], "evaluate_model": [10, 11, 13], "even": 18, "evenli": 14, "ever": 17, "everi": [0, 2, 3, 4, 7, 8, 13, 14, 16, 18, 19, 21, 22, 24, 25], "everyon": [], "everyth": [5, 10, 12, 14, 16, 17, 18, 19, 24], "everywher": [0, 5], "evid": 13, "evolut": [14, 16], "evolv": [], "exact": [6, 17], "exactli": [7, 25], "exampl": [0, 14, 17, 25], "exchang": 17, "execut": [0, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 17, 19, 22], "executepreprocessor": 17, "exercis": [16, 18], "exist": [5, 8, 16, 17, 25], "exp": [2, 8, 19], "expect": [2, 3, 4, 5, 17], "expected_runtime_dai": 14, "experi": [0, 13, 14, 18, 22, 24], "experiment": [10, 13, 19], "experiment_manag": 14, "experiment_result": 14, "experimentmanag": 14, "expert": [9, 10, 11, 12, 14, 18], "expertis": 16, "explain": [19, 25], "explicit": 5, "explod": 3, "exploit": 9, "explor": [9, 18], "exponenti": 1, "export": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 16, 21, 22], "express": [4, 8], "extend": [8, 10, 15, 16, 20, 22, 24, 25], "extens": [10, 16], "extract": [5, 7], "extrem": [2, 6], "f": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 19], "f1": 3, "f2": 3, "f3": 3, "f_": 4, "f_1": 4, "f_n": 4, "fail": 17, "failing_modul": 21, "failur": [7, 10, 14, 17], "fair": 17, "fall": 2, "fallback": 0, "fals": [7, 10, 19], "famili": 5, "familiar": [15, 17, 23], "fast": [9, 11, 12], "faster": [11, 12, 19], "fastest": 2, "fault": 14, "featur": [2, 3, 4, 5, 7, 10, 14, 19, 24], "feature_engin": 14, "feature_map": 5, "feder": 10, "feed": [4, 5, 7], "feedback": [2, 3, 4, 5, 7, 14, 21, 25], "feedforward": 15, "feel": [16, 18], "ff6b6b": [], "ffeaa7": [], "fff": [], "field": [5, 6, 25], "figur": 25, "file": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 17], "filepath": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15], "fill": [], "filter": [4, 5], "final": [3, 4, 5, 9, 10, 11, 14, 17, 19, 22, 25], "final_s": 11, "financi": 8, "find": 13, "finish": 16, "first": [0, 3, 7, 8, 9, 12, 17, 19, 22, 23, 24], "firsthand": 18, "fit": [7, 10, 14, 18, 23, 25], "fix": [6, 17, 21], "flag": 17, "flame": 0, "flatten": [3, 4, 5, 7, 10], "flexibl": [7, 18], "float": 0, "float32": 12, "float64": 1, "flop": 25, "flow": [4, 6, 8, 25], "focu": [15, 18, 19, 21], "focus": [13, 18, 20], "folder": 17, "follow": [0, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 18, 19, 20, 21, 22, 24], "fork": [18, 23], "form": [], "format": [0, 7, 13, 17], "formula": 2, "forum": 22, "forward": [3, 4, 5, 6, 8, 9, 10, 18, 19, 24, 25], "found": 17, "foundat": [1, 2, 4, 5, 6, 7, 10, 11, 12, 13, 14, 15, 17, 21, 23, 25], "fp32": 11, "fp32_memori": 12, "framework": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 14, 15, 16, 17, 22, 23, 24, 25], "frequent": 19, "fresh": 17, "fridai": 17, "friendli": 12, "from": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 20, 21, 22, 23, 24, 25], "full": [0, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 15, 18, 21, 22, 25], "fulli": [16, 17, 18, 21, 22], "function": [3, 5, 6, 7, 8, 9, 11, 12, 13, 14, 15, 16, 17, 19, 20, 21, 22, 23, 24, 25], "fundament": [1, 3, 6, 16, 19], "futur": [6, 15], "g": 16, "gain": [12, 23], "gamma": 9, "gan": 2, "gap": [11, 12, 18, 22, 25], "gate": 2, "gave": 22, "gener": [2, 4, 5, 6, 10, 13, 15, 16, 22, 24, 25], "generate_comprehensive_report": 13, "georg": 20, "get": [18, 23], "get_config": 14, "get_full_profil": 0, "get_last_lr": 9, "get_learning_path": [], "get_learning_recommend": [], "get_model": 14, "get_num_class": 7, "get_recent_data": 14, "get_required_check": 14, "get_tinytorch_overview": [], "gh": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15], "git": [17, 22, 24], "github": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 17, 22, 24], "give": [2, 5, 6, 8, 9, 20], "glanc": 22, "global": [6, 9], "glorot": 3, "go": 25, "goal": [10, 19], "good": [9, 19], "goodfellow": 20, "googl": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15], "got": 25, "governance_check": 14, "governanceengin": 14, "gpt": [4, 6, 8, 9, 10, 15, 16, 18, 24, 25], "gpu": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 18, 25], "grace": [0, 3], "grad": [8, 9, 18, 19, 25], "grad_output": [19, 25], "grade": [14, 18, 24], "gradebook": 17, "gradient": [3, 6, 8, 9, 10, 15, 16, 18, 24, 25], "gradient_descent_step": 9, "gradual": 4, "graduat": 22, "granular": 16, "graph": [13, 18, 24, 25], "grasp": 6, "great": [20, 23], "green": 17, "ground": 5, "ground_truth": 14, "group": 19, "grow": [6, 7, 16], "gru": 2, "guarante": 9, "guid": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 22, 23], "guidanc": [11, 16, 24], "guidelin": 4, "gz": 17, "g\u00e9ron": 20, "h": [], "h1": [3, 8], "ha": [17, 19, 21, 25], "habit": 0, "hand": [5, 18, 20, 23], "handl": [0, 1, 2, 3, 4, 5, 7, 8, 10, 13, 14, 18, 19, 24, 25], "happen": [4, 5, 15, 17, 18, 19, 22, 25], "hard": [10, 19], "harder": 19, "hardwar": [11, 13, 14, 17, 18, 22, 24, 25], "harrison": 20, "harvard": [18, 20], "have": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 19, 21, 23, 24], "head": [4, 5, 6, 15], "health": [10, 14, 17, 18, 22, 24], "health_awar": 14, "health_check_interv": 14, "healthcheck": 14, "heart": [5, 8, 10], "heavi": 20, "height": 5, "hello": 0, "hello_tinytorch": [0, 24], "help": [2, 20], "here": [0, 17], "hidden": [2, 3, 4, 17, 19], "hidden_s": 4, "hierarch": [2, 4, 5], "hierarchi": [12, 19], "high": [7, 13, 14, 16, 18, 19, 23, 24], "higher": [1, 5, 8], "hire": [22, 25], "histori": 10, "hobbi": 7, "hood": [18, 20, 23], "hope": 25, "horizont": 16, "hotz": 20, "hour": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15], "hous": 4, "how": [0, 1, 3, 4, 5, 6, 8, 9, 10, 12, 15, 20, 22, 23, 24, 25], "html": [13, 14, 17], "http": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 17, 22, 24], "human": [6, 10, 15], "huyen": 20, "hyperparamet": [9, 10], "i": [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 12, 14, 15, 16, 17, 19, 21, 23, 24, 25], "ian": 20, "id": 14, "ident": [2, 7, 12], "identifi": [8, 11, 12, 13, 14, 19], "ignor": 6, "im2col": 19, "imag": [1, 2, 3, 4, 5, 6, 7, 23, 24], "image_batch": 5, "image_classifier_optim": 14, "image_classifier_v2": 14, "imagenet": [5, 7, 13], "imagenet_subset": 13, "immedi": [2, 3, 16, 18, 21, 22], "impact": [11, 12, 14], "implement": [6, 17, 18, 19, 21, 22, 23, 24, 25], "implic": [18, 25], "import": [1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 16, 18, 21, 24, 25], "importance_threshold": 11, "improv": [7, 10, 11, 12, 13, 14, 22, 24, 25], "improved_model": 14, "in_channel": [5, 19], "in_featur": 25, "inact": 23, "includ": [0, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 17, 18, 21, 22, 24], "incompat": 0, "incomplet": 7, "increas": [4, 5, 7], "independ": [19, 25], "index": 7, "indic": [7, 24], "individu": [7, 17, 21], "induct": 4, "industri": [0, 13, 14, 25], "infer": [4, 7, 11, 12, 14, 18], "infinitesim": 8, "influenc": 5, "info": [17, 24], "inform": [4, 6, 16], "infrastructur": [7, 17, 18, 20, 24, 25], "inherit": 19, "init": [17, 22], "initi": [3, 5, 8, 9, 22, 24], "inlin": 24, "innov": 15, "inplac": 19, "input": [2, 3, 4, 5, 6, 8, 9, 14, 19], "input_imag": 5, "input_img": 5, "input_s": [3, 4], "input_shap": 13, "input_tensor": 18, "insid": 22, "insight": [3, 5, 8, 9, 23], "inspir": 18, "instabl": 25, "instal": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 18, 22, 23, 24], "instanc": 14, "instantli": [21, 22], "instead": [18, 25], "instruct": [12, 17, 19], "instructor": [0, 18], "int32": 12, "int8": [11, 12], "int8_memori": 12, "intact": 21, "integr": [0, 2, 5, 7, 11, 12, 13, 17, 22, 24, 25], "intel": 12, "intellig": [2, 3, 4, 9, 10, 11, 12], "interact": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 18], "interfac": [0, 3, 5, 7], "intermedi": [1, 2, 3, 8], "intern": [24, 25], "interpret": [2, 6, 10, 17], "interv": 13, "interview": 25, "introduc": 0, "introduct": [0, 22], "introduction_dev": [], "intuit": [18, 25], "invalid": 3, "invari": [3, 5], "invers": 8, "invest": 17, "investig": 21, "invis": 8, "invit": 19, "iot": 11, "ipynb": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 17], "is_compat": 0, "isn": [18, 19], "isol": 21, "issu": [2, 7, 10, 21, 22, 24, 25], "item": [3, 4], "iter": [0, 7], "its": [8, 15], "itself": 19, "j": [5, 12, 19], "jacobian": 8, "janapa": [18, 20], "jax": 8, "jit": 12, "job": [22, 25], "journei": [0, 14, 20, 25], "json": 14, "jsonifi": 14, "jump": 24, "jupyt": [1, 17, 23, 24], "jupytext": 17, "just": [2, 3, 7, 12, 16, 17, 18, 19, 21, 22, 23, 25], "k": [0, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14], "k_h": 19, "k_w": 19, "karpathi": 20, "kei": [18, 22], "kernel": [6, 10, 11, 13, 14, 16, 18, 19, 22, 24], "kernel_s": [5, 10, 19], "kernels_dev": 12, "kinemat": 8, "kinslei": 20, "know": [6, 17, 18, 21], "knowledg": [0, 19, 20, 25], "kwarg": 19, "l": [9, 17], "l1": 12, "l2": 12, "l3": 12, "lab": [17, 18, 24], "label": 7, "lack": 20, "landscap": [9, 10], "languag": [2, 3, 4, 6, 7, 9, 18, 20, 23, 24, 25], "languagemodelloss": 15, "languagemodeltrain": 15, "larg": [7, 9, 11], "large_batch": 12, "larger": [7, 11, 18, 22, 25], "last_input": 19, "latenc": [11, 13, 14], "latency_m": 14, "latency_p99_m": 14, "later": 5, "launch": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 18], "layer": [1, 2, 4, 5, 6, 7, 8, 10, 11, 14, 15, 16, 17, 18, 19, 22, 24], "layer1": [3, 8], "layer2": [3, 8], "layer_1": 4, "layer_2": 4, "layer_idx": 11, "layer_n": 4, "layernorm": 15, "layers_dev": [3, 4, 10, 11, 13], "layout": [1, 12], "leadership": 25, "leaf": 8, "learn": [17, 19, 21, 23], "learnabl": 5, "learner": [14, 19], "learning_path": [], "learning_r": [9, 10], "len": 7, "length": [6, 18, 25], "let": [15, 18, 22], "level": [5, 12, 13, 15, 16, 18, 19, 23], "leverag": [2, 5, 25], "librari": [8, 12, 22, 24], "lifecycl": [17, 20], "like": [0, 2, 3, 5, 6, 7, 10, 11, 12, 13, 16, 18], "limit": [11, 18, 25], "line": [12, 16, 17, 18, 19, 20], "linear": [3, 4, 12, 16, 18, 24, 25], "list": 19, "live": [13, 23], "ll": 17, "lm": 17, "load": [0, 10, 14, 16, 18, 24], "load_balanc": 14, "load_checkpoint": 10, "load_model": 13, "load_pretrained_large_model": 11, "loadbalanc": 14, "loader": 7, "local": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 17, 18, 23], "locat": 10, "log": [8, 10, 14, 17], "log_outcom": 14, "log_predict": 14, "logger": 14, "logic": [10, 19], "logit": 10, "long": [15, 17], "look": [6, 17, 21], "loop": [1, 5, 7, 9, 10, 11, 14, 15, 16, 17, 18, 19, 22, 24, 25], "loss": [7, 8, 9, 11, 15, 17, 18, 19, 24, 25], "loss_fn": [10, 14, 19], "low": [12, 19], "lr": [9, 10, 18, 19], "lstm": 2, "m": [0, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 17, 19, 22], "m_t": 9, "machin": [0, 1, 3, 6, 7, 8, 15, 18], "mae": 10, "magic": [4, 15, 16, 19, 24], "magnitud": 11, "main": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15], "maintain": [11, 12], "major": [2, 12, 13, 22], "make": [4, 6, 8, 9, 10, 11, 12, 14, 18, 19, 24], "manag": [0, 1, 3, 5, 7, 8, 9, 15, 16, 18, 22, 24, 25], "mani": 19, "manipul": 1, "manual": 17, "map": [0, 5, 11, 12, 25], "mark": 16, "marker": 17, "masked_fil": 6, "master": [0, 4, 5, 6, 8, 9, 10, 11, 12, 13, 18, 21], "masteri": [0, 14, 16, 18, 24], "match": [2, 3, 5, 12], "math": [0, 6, 8, 12, 19, 20, 23], "mathemat": [4, 6, 10, 15, 16, 17, 18, 20, 22, 24], "matmul_baselin": 12, "matric": [1, 12, 25], "matrix": [3, 8, 10, 12, 15, 17, 18, 23, 24, 25], "matter": [3, 18, 23, 25], "max": [1, 2, 7, 12], "max_concurrent_request": 14, "max_latency_m": 13, "max_latency_p99": 13, "max_length": 6, "max_tim": 12, "maximum": [2, 11, 12, 18, 19], "maxpool": 5, "maxpool2d": [5, 10], "mb": 11, "md": 18, "me": 22, "mean": [1, 7, 11, 12, 18, 19], "mean_tim": 12, "meanabsoluteerror": 10, "meaning": 13, "meansquarederror": 10, "measur": [10, 11, 12, 13, 24], "measure_memory_usag": 12, "mechan": [2, 6, 9, 16, 17, 18, 22, 25], "medic": 5, "medium": 14, "meet": [8, 12, 13, 14], "meets_constraint": 13, "meets_production_criteria": 14, "meets_sla": 13, "memori": [2, 7, 8, 9, 12, 13, 16, 18, 19, 24, 25], "memory_format": 19, "memory_limit_mb": 13, "memory_reduct": 12, "memory_usag": 14, "mental": [], "messag": [17, 21, 24], "metadata": 14, "method": [1, 3, 9, 11, 19], "methodologi": 14, "metric": [11, 13, 14, 24], "micrograd": [18, 20], "midterm": 17, "might": 3, "mileston": 16, "min": [1, 7, 12], "min_run": 13, "min_tim": 12, "mindset": 18, "minim": [9, 18, 21], "minima": 9, "minimalist": 18, "minimum": [0, 9, 13], "minimum_detectable_effect": 14, "minitorch": 18, "minor": 21, "minut": [17, 18, 19, 22, 23, 25], "mirror": [0, 1, 16], "mislead": 13, "mismatch": 3, "miss": [0, 12, 18, 25], "mit": 20, "mix": 25, "mkdir": 17, "mkl": 12, "ml": [0, 8, 10, 12, 13, 15, 16, 17, 20, 22, 23, 24], "mlop": [0, 9, 10, 11, 12, 13, 16, 18, 22, 24, 25], "mlops_dev": 14, "mlopsplatform": 14, "mlp": 4, "mlperf": [17, 24], "mlsysbook": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15], "mobil": [11, 13], "mobile_benchmark": 13, "mobile_feas": 13, "mobile_model": 11, "mobile_result": 13, "modal": [15, 16, 25], "mode": [8, 10], "model": [2, 3, 6, 7, 8, 9, 12, 13, 17, 18, 19, 20, 23, 24, 25], "model_approval_requir": 14, "model_evalu": 14, "model_explainability_requir": 14, "model_fp32": 12, "model_govern": 14, "model_id": 14, "model_int8": 12, "model_train": 14, "model_v2_0": 14, "model_v2_1": 14, "modelmetadata": 14, "modelmonitor": 14, "modelregistri": 14, "modelserv": 14, "moder": 2, "modern": [2, 5, 8, 9, 10, 12, 16, 18], "modif": 25, "modifi": [19, 23], "modul": [20, 25], "modular": 3, "module_nam": 17, "module_xx": 21, "moment": [9, 14], "momentum": [9, 25], "mondai": 17, "monitor": [7, 10, 16, 18, 24, 25], "monitoring_config": 14, "more": [4, 5, 9, 11, 18, 19, 23, 25], "most": [2, 3, 6, 9, 12, 15, 17, 18, 19, 20, 22, 24, 25], "move": [5, 12, 25], "mri": 5, "mse": 10, "mse_loss": [10, 18], "mseloss": 18, "multi": [4, 6, 10, 12, 14, 15, 16, 17, 18, 22, 24], "multiheadattent": 15, "multimod": 6, "multipl": [1, 3, 5, 7, 8, 10, 11, 12, 13, 14, 15, 17, 18, 19, 21, 22, 23, 24], "multipli": 8, "multiprocess": 12, "music": 14, "my": [16, 22, 24, 25], "mybind": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15], "myself": [18, 24], "n": [4, 6, 10], "naiv": [18, 25], "name": [0, 14, 16, 17, 19, 24], "natur": [2, 3, 4, 6, 7, 20], "navig": [1, 5], "nbdev": 0, "nbgrader": [18, 22, 24, 25], "nbgrader_config": 17, "necessari": 25, "need": [13, 16, 17, 18, 23, 25], "neg": [0, 2], "nest": [3, 4, 19], "netflix": [7, 10, 14], "network": [1, 2, 5, 6, 7, 9, 10, 11, 12, 14, 16, 17, 18, 20, 22, 23, 24], "networks_dev": [4, 10, 11, 13], "networkx": [], "neural": [1, 2, 4, 7, 9, 10, 11, 12, 14, 17, 18, 20, 22, 23, 24], "neuron": 11, "neurons_to_remov": 11, "new": [9, 14, 16, 17, 24], "new_data": 14, "next": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17], "next_modul": [], "nlp": 20, "nn": [18, 19, 25], "nnf": 20, "node": 8, "non": [2, 9], "none": [6, 19], "nonlinear": [3, 4, 5, 15, 16, 17, 22, 23, 24], "nopython": 12, "normal": [7, 15], "normalized_imag": 7, "north": 10, "note": 22, "notebook": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 17, 22, 24], "notimplementederror": 17, "now": [7, 8, 10, 15, 16, 22, 23, 24, 25], "np": [12, 18, 19, 25], "nrais": 17, "num_class": [4, 10, 13], "num_cor": 12, "num_epoch": 9, "num_featur": 10, "num_run": 12, "num_work": 12, "numba": 12, "number": [1, 8], "numer": 8, "numpi": [1, 2, 12, 18], "nvidia": 12, "n\u00b2": [6, 18, 25], "o": [6, 7, 18, 25], "object": 19, "obscur": 19, "off": [4, 7, 11, 18], "offlin": 13, "offset": 11, "often": [9, 19, 21], "onboard": 0, "onc": [0, 7, 17], "one": [3, 7, 15, 18, 19], "ones": 19, "ongo": 23, "onli": [5, 15, 18, 22], "onlin": [9, 14], "op": 16, "opaqu": 19, "open": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 17, 24], "openbla": 12, "oper": [0, 2, 3, 6, 7, 8, 14, 16, 18, 19, 20, 21, 22, 23, 24, 25], "opportun": [22, 25], "optim": [0, 2, 3, 8, 13, 14, 15, 16, 17, 18, 20, 22, 24, 25], "optimization_result": 13, "optimize_infer": 14, "optimized_model": [11, 13, 14], "optimized_op": 12, "optimized_result": [12, 13], "optimized_stat": 12, "optimized_tim": 12, "optimized_v2": 13, "optimizers_dev": [9, 10], "option": [3, 19], "orchestr": [10, 14, 16, 18], "order": [7, 8, 15], "org": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 17, 22, 24], "organ": [24, 25], "orient": [0, 19], "origin": [7, 11, 18], "original_acc": 11, "original_param": 11, "original_s": 11, "other": [5, 18, 20, 21], "our": [7, 10, 21, 22, 25], "out": 25, "out_channel": [5, 19], "out_featur": 25, "outcom": 14, "output": [0, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 16, 17, 18, 19, 21], "output_activ": 4, "output_height": 19, "output_pad": 19, "output_s": [3, 4], "output_shap": 19, "output_width": 19, "over": [12, 14, 18], "overal": [17, 21], "overfit": 10, "overflow": [2, 7, 12], "overview": [16, 17], "own": [22, 23, 24, 25], "p": [1, 17], "pace": [18, 22], "packag": [0, 16, 24, 25], "pad": [5, 6, 19], "padding_mask": 6, "padding_mod": 19, "pai": 6, "paper": [13, 25], "parallel": [6, 12, 15], "parallel_batch_process": 12, "parallel_relu": 12, "parallel_tim": 12, "param": [18, 19], "param_count": 11, "paramet": [4, 5, 8, 9, 10, 11, 19, 25], "pars": 7, "parser": [], "part": [15, 18], "particip": 22, "pass": [1, 3, 4, 5, 7, 8, 9, 10, 12, 17, 18, 19, 21], "patch": 6, "path": [8, 18, 19, 21], "pattern": [2, 6, 9, 12, 13, 15, 16, 18, 24, 25], "pdf": 13, "peak": [19, 25], "pedagog": 18, "pedagogi": 25, "per": [9, 17, 19, 22], "percentil": 13, "percept": [4, 5], "perceptron": 24, "perf_count": 12, "perfect": [20, 22, 23, 24], "perform": [3, 4, 5, 8, 10, 11, 14, 16, 17, 18, 20, 21, 22, 25], "performance_evalu": 13, "performance_metr": 14, "performance_monitoring_requir": 14, "performance_threshold_drop": 14, "performance_valid": 14, "performanceprofil": 12, "performancereport": 13, "persist": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 23, 24], "person": [0, 14, 18, 25], "perspect": 20, "philosophi": [0, 3, 16, 19], "photo": 5, "physic": [3, 8, 9], "pictur": 14, "piec": [10, 18], "pip": [17, 22], "pipelin": [0, 5, 14, 16, 17, 18, 20, 22, 24, 25], "pixel": 7, "pkl": 10, "place": 17, "placement": 4, "plan": [4, 7, 11], "platform": [0, 10, 13, 14], "plot": [2, 4], "plot_training_histori": 10, "pocket": 11, "point": [0, 2, 12, 13, 17], "polici": 9, "pool": [5, 12], "portfolio": [8, 22, 25], "posit": [2, 5, 6, 15, 22], "positionalencod": 15, "possibl": [8, 9, 19, 24], "power": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 18, 23, 24], "pptx": 13, "practic": [2, 9, 11, 12, 14, 18, 20, 22, 24, 25], "practition": [18, 25], "pre": 23, "precis": [11, 12, 25], "pred": [18, 19], "predefin": 16, "predict": [2, 3, 4, 5, 7, 9, 10, 14, 15, 19], "predict_with_experi": 14, "prefer": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 19], "prepar": [5, 10, 13, 16, 25], "preprocess": [14, 16, 24], "preprocessed_input": 14, "prerequisit": 6, "present": [13, 17], "preserv": [2, 3, 5, 11, 12], "prevent": [2, 3, 6, 7, 10, 12, 13, 15], "previou": [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 19, 21], "price": 4, "primit": [1, 16, 18], "principl": [4, 5, 8, 9, 11, 12, 25], "print": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14], "priorit": 19, "prioriti": 17, "probabilist": 2, "probabl": [2, 3, 4, 5], "problem": [2, 4, 6, 9, 10, 18, 19], "process": [1, 2, 3, 4, 5, 6, 7, 10, 11, 12, 13, 16, 20, 24], "produc": [4, 7, 12], "product": [0, 1, 10, 12, 13, 16, 17, 19, 21, 25], "production_deploy": 14, "production_readi": 13, "prof": [18, 20], "profession": [0, 18, 22, 24], "professor": 22, "profil": [11, 16, 17, 18, 19, 25], "profile_oper": 12, "program": [12, 18, 25], "programmat": [], "progress": [17, 18, 19, 22, 25], "project": [0, 7, 17, 18, 20, 23, 25], "promote_winn": 14, "propag": [8, 24], "proper": [0, 1, 2, 3, 4, 5, 9, 10, 11, 12, 13, 15], "properli": [9, 21], "properti": [1, 3, 8], "prototyp": [7, 11], "prove": [13, 18], "proven": [18, 25], "provid": [0, 2, 12, 16, 17, 18, 20, 21, 22, 24, 25], "prune": [12, 13, 17, 24], "prune_layer_neuron": 11, "prune_model_by_magnitud": 11, "prune_redundant_neuron": 11, "pruned_acc": 11, "pruned_model": 11, "pruned_s": 11, "pt": 14, "public": 13, "publish": 16, "purpos": 19, "py": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 21, 24], "pytest": [0, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14], "python": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 21, 24], "python3": [17, 22], "pytorch": [0, 1, 8, 12, 16, 18, 19, 20, 22, 25], "q": 6, "qa": 16, "qk": 6, "quadrat": [9, 18], "qualifi": 25, "qualiti": [7, 11, 14], "quantit": 2, "quantiz": [13, 14, 17, 24], "quantize_model": 14, "quantize_model_weight": 11, "quantized_acc": 11, "quantized_matmul": 12, "quantized_model": 11, "quantized_s": 11, "queri": 6, "question": [18, 19, 24, 25], "r": [5, 17, 19, 22], "rai": 5, "randn": [12, 25], "random": [7, 12, 25], "rang": [2, 3, 7, 9, 12, 17, 19], "rate": [10, 17, 22, 24], "rather": 16, "ratio": 11, "re": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 17, 18], "reach": [9, 14], "read": [17, 20, 22], "readi": [6, 15, 16, 17, 21, 22, 23], "real": [18, 20, 21, 22, 23, 25], "realist": [11, 25], "realiti": [18, 25], "realli": [0, 1, 8, 12], "reason": 2, "recent": [21, 22], "recept": [5, 6], "recogn": [3, 4, 9], "recognit": [2, 5, 16], "recommend": [0, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 21], "record": 17, "recov": 11, "recoveri": [0, 7, 14], "reddi": [18, 20], "reduc": [4, 5, 7, 11, 24], "reduct": [1, 5, 11, 12, 16], "refer": [12, 13, 22], "reference_dataset": 14, "reflect": [], "regardless": 5, "region": 5, "regist": 14, "register_model": 14, "registri": 14, "regress": [4, 10], "regression_loss": 10, "regressor": 4, "regul": 14, "regular": 22, "reinforc": 9, "relationship": [5, 15, 23], "releas": [22, 24], "relev": [22, 25], "reli": [2, 9, 18], "reliabl": [12, 13, 14, 18, 21, 24], "relu": [3, 4, 5, 8, 9, 10, 11, 12, 13, 18, 19, 23, 24], "remaining_tim": [], "rememb": 19, "remov": [11, 17], "repeat": 18, "repl": 1, "repo": [17, 18, 23], "report": [16, 17, 22, 24], "repres": [4, 8, 16], "represent": [4, 5], "reproduc": [7, 10, 13], "request": [13, 14], "requir": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 17, 18, 19, 21, 22], "requires_grad": [8, 9], "research": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 18, 25], "reshap": 1, "residu": [5, 15], "resnet": [2, 3, 4, 5, 9], "resourc": 0, "respect": 8, "respons": 0, "restor": 10, "result": [3, 8, 10, 12, 13, 16, 17, 18, 19, 23], "results_summari": 13, "retrain": 14, "retraining_schedul": 14, "retriev": 14, "return": [6, 7, 8, 10, 11, 12, 14, 17, 18, 19, 25], "reus": [15, 16, 18, 24, 25], "reusabl": [3, 5, 7, 15], "revers": 8, "review": [17, 21], "revolut": 6, "revolution": 5, "rgb": 7, "rhythm": 0, "rich": 17, "rigor": 13, "risk": 8, "rnn": [2, 3, 6], "robot": 8, "robust": [1, 7, 10, 21], "rocket": [], "role": [2, 15, 16, 18, 25], "role_based_access": 14, "rollback": 14, "round_robin": 14, "rout": 14, "row": 12, "rows_a": 12, "rows_b": 12, "rtol": 12, "rule": [1, 8, 9, 19], "run": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 23], "run_all_modul": 21, "run_all_scenario": 13, "run_integration_test": 21, "runner": 21, "runtim": 11, "s965": 20, "safe": 14, "safeti": [11, 14], "same": [3, 4, 5, 8, 10, 14, 15, 18, 19, 20, 21, 23], "sampl": [7, 13, 15], "sample_batch": 7, "sample_data": 4, "satisfi": 23, "save": [23, 25], "save_as_html": 13, "save_as_pdf": 13, "save_best": 10, "save_checkpoint": 10, "save_summary_t": 13, "scaffold": [0, 18], "scalabl": [7, 10, 14], "scalar": [1, 12], "scale": [4, 7, 9, 11, 12, 14, 18, 20, 25], "scale_a": 12, "scale_b": 12, "scale_c": 12, "scaled_dot_product_attent": 6, "scan": 5, "scenario": [0, 2, 3, 4, 10, 11, 17, 21], "schedul": [14, 17, 22, 24], "scienc": [12, 22, 25], "scientif": [1, 3, 8], "scientist": [13, 25], "scope": [], "score": [6, 17, 22], "scratch": [5, 6, 12, 18, 20, 22, 23, 24, 25], "script": 17, "seamless": [3, 8], "seamlessli": [3, 7, 15, 18, 21], "search": 10, "sec": 13, "second": [9, 12, 13], "section": [0, 2, 18, 25], "secur": 14, "see": [3, 5, 6, 15, 16, 17, 18, 19, 20, 22, 23, 24], "seem": 3, "select": [9, 10, 20], "self": [4, 7, 10, 12, 17, 18, 19, 25], "selfattent": [6, 15], "semest": 7, "senior": 22, "sensit": [8, 9], "sensor": 7, "separ": [7, 11, 13, 16, 18], "seq_len": 6, "sequenc": [6, 15, 16, 25], "sequenti": [5, 6, 7, 9, 10, 11, 13, 18, 24], "sequential_relu": 12, "seriou": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 18, 23], "serv": [1, 11, 16, 18], "server": [13, 14, 17], "server1": 14, "server2": 14, "server3": 14, "server_benchmark": 13, "server_result": 13, "serving_config": 14, "session": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 23], "set": [13, 17, 22], "set_dataset": 13, "set_metr": 13, "set_model": 13, "setup": [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 18, 22], "setup_dev": [0, 24], "sever": [11, 14], "sgd": [9, 16, 17, 18, 22, 24, 25], "sh": [0, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 24], "shallow_net": 4, "shape": [1, 2, 3, 4, 5, 6, 7, 8, 12], "share": [5, 15, 17, 23], "shift": [7, 15], "ship": 11, "short": 16, "should": [1, 8, 10, 17, 21, 25], "show": [2, 4, 5, 10, 12, 15, 16, 17, 18, 19, 20, 21, 24], "shuffl": [7, 10, 24], "side": 19, "sigmoid": [3, 4, 5, 19, 24], "sigmoid_output": 10, "signatur": 0, "signific": [12, 13, 21], "significance_level": 14, "significant_improv": 14, "simd": 19, "similar": [0, 1, 7, 10, 12, 16], "simpl": [2, 3, 4, 5, 8, 9, 10, 21, 23], "simpledataset": 10, "simpler": 19, "simplest": 19, "simpli": 3, "simplic": 19, "simplifi": 15, "simul": 3, "simultan": [1, 6], "sin": 8, "singl": [1, 4, 12, 13], "single_stream": 13, "single_tim": 12, "sinusoid": 15, "size": [1, 4, 6, 7, 10, 11, 12, 13, 16, 24, 25], "skill": [12, 22], "skip": [5, 16], "slide": [5, 13, 19], "slow": 18, "slower": [18, 25], "small": [9, 11], "smaller": [11, 12], "smallest": 11, "smart": 1, "smartphon": [11, 12], "smooth": 2, "smoother": 9, "so": [5, 18], "softmax": [4, 6, 10, 24], "softwar": [8, 12, 13, 18, 25], "solid": [0, 1, 18, 25], "solut": [0, 9, 16, 17, 18, 19, 25], "solv": [4, 9, 18], "some": [9, 21], "someon": 4, "someth": [0, 1, 8, 10, 19, 22], "sometim": 19, "soon": 22, "sophist": 3, "sort": 8, "sourc": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 17, 22, 24], "span": [], "spark": 6, "spars": [2, 11], "spatial": [5, 6, 16, 18, 20, 22, 24], "spatial_dev": 5, "special": [16, 25], "specif": [4, 11, 16, 17, 21, 22, 24, 25], "specifi": 17, "speed": [9, 11, 18, 19, 20, 25], "speedup": [11, 12, 13, 25], "spend": 25, "split": [7, 14], "spotifi": [7, 14], "sqrt": [6, 19], "squar": 8, "stabil": [3, 8, 9], "stabl": [2, 3, 9, 15], "stack": [14, 24, 25], "stai": [], "stakehold": 13, "standalon": 16, "standard": [0, 3, 4, 13, 14, 22], "stanford": 20, "star": 10, "start": [17, 25], "start_tim": 14, "startup": [7, 22], "state": [3, 6, 9, 10, 19, 25], "statement": 17, "static": 8, "statist": [4, 7, 12, 14, 24], "statistical_signific": 12, "statisticalvalid": 13, "statu": [16, 18, 22, 24], "std": [7, 11, 12], "std_time": 12, "step": [0, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 16, 18, 19], "step_siz": 9, "steplr": 9, "stop": [10, 25], "storag": [1, 7, 8], "store": [1, 8, 14], "straightforward": 19, "strateg": [0, 9, 11, 15], "strategi": [3, 7, 8, 9, 10, 11, 14, 24, 25], "stream": [7, 13], "stride": [5, 19], "stroke": [], "stronger": 2, "structur": [0, 4, 5, 11, 12, 16, 18, 19, 21, 22, 25], "stub": 17, "student": [11, 18, 19, 21], "student_model": 11, "student_nam": 17, "student_output": 11, "style": [6, 12, 13, 15, 16, 17, 18, 24], "submiss": 24, "submit": 17, "subsequ": 0, "subset": 10, "subset_s": 13, "subtract": 1, "success": [7, 15, 24], "successfulli": [7, 10, 14, 16, 17], "suffici": [4, 13], "suggest": [16, 24], "suit": 21, "suitabl": 13, "sum": [1, 5, 8, 9, 19], "summari": 13, "support": [0, 8, 10, 14, 15, 16, 17, 24, 25], "suscept": 2, "switch": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15], "symmetr": 2, "sync": 0, "syntax": 19, "synthet": [10, 13], "system": [1, 2, 3, 4, 5, 6, 12, 15, 19, 23], "systemat": [10, 12, 13, 16, 18, 21, 24], "systeminfo": 0, "t": [1, 6, 9, 18, 19, 22, 25], "ta": 17, "tabl": [13, 16], "tackl": [20, 22], "tag": 5, "take": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 17], "tanh": [3, 24], "tar": 17, "target": [6, 9, 10, 11, 15, 18], "target_size_mb": 11, "target_throughput": 13, "task": [4, 5, 6, 11, 18], "td": [], "teach": [0, 3, 4, 5, 6, 7, 11, 12, 13, 15, 18, 19, 20, 23], "teacher": 11, "teacher_model": 11, "teacher_output": 11, "team": [18, 24, 25], "tech": 22, "technic": [13, 17, 22], "techniqu": [10, 16, 25], "technologi": 5, "temperatur": 11, "temporari": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 17, 23], "tensor": [0, 2, 3, 4, 5, 6, 7, 8, 9, 10, 14, 15, 16, 17, 18, 19, 21, 22, 23, 24, 25], "tensor_dev": 1, "tensorflow": [1, 8, 12, 18], "term": 3, "termin": 17, "tesla": 14, "test": [17, 18, 22, 25], "test_data": [7, 13], "test_dataset": 13, "test_imag": 7, "test_input": 4, "test_label": 7, "test_load": [7, 10, 11], "test_module_depend": 21, "text": [6, 7, 15, 16, 22, 24], "textgener": 15, "than": [2, 16, 18, 19, 22, 24, 25], "thei": [1, 3, 7, 9, 11, 14, 17, 18, 22, 25], "them": [2, 4, 18, 21, 25], "theori": [2, 18, 22], "thi": [0, 1, 2, 3, 4, 5, 6, 8, 9, 11, 12, 13, 14, 17, 19, 21, 23, 25], "thing": 19, "think": [7, 11, 12, 13, 14, 15, 18, 19], "third": 12, "thorough": 13, "thoroughli": [0, 1, 9], "those": [2, 4, 18], "thoughtfulli": 4, "thread": 12, "three": [2, 18], "threshold": 14, "through": [2, 3, 4, 5, 8, 11, 12, 16, 17, 18], "throughout": 0, "throughput": [7, 11, 12, 13, 14], "time": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14], "timelin": [], "timeout": [17, 23], "timeout_m": 14, "tini": [18, 20], "tinygpt": [16, 18, 22, 24], "tinygpt_dev": 15, "tinygrad": [18, 20], "tinyml": 20, "tinytorch": [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 20, 23, 24], "tinytorchanalyz": [], "tinytorchperf": 13, "tito": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 16, 17, 18, 21, 22], "todo": 0, "togeth": [0, 3, 10, 14, 16, 18, 21, 22, 23, 24], "toi": [7, 24, 25], "token": [6, 15, 16, 18], "toler": 14, "tolist": [1, 14], "too": [16, 19], "tool": [0, 4, 7, 11, 12, 15, 16, 18, 19, 20, 25], "toolkit": 18, "top": 15, "topic": [], "topolog": 8, "torch": [18, 19, 25], "total": 1, "touch": 19, "toward": [4, 16], "tpu": 12, "track": [4, 7, 8, 9, 10, 14, 18, 22, 24], "track_business_metr": 14, "track_infer": 14, "track_infrastructure_metr": 14, "track_performance_metr": 14, "trade": [4, 7, 11, 18], "tradit": [16, 18], "traffic": 14, "traffic_percentag": 14, "traffic_splitt": 14, "trafficsplitt": 14, "trail": 14, "train": [0, 1, 3, 4, 5, 6, 7, 8, 11, 12, 13, 14, 17, 21, 25], "train_acc": 10, "train_accuraci": 10, "train_data": 7, "train_dataload": 10, "train_dataset": 10, "train_improved_model": 14, "train_label": 7, "train_load": [7, 10, 11, 14], "train_loss": 10, "train_step": 19, "trainabl": 8, "trained_model": [11, 14], "trainer": [10, 14, 19], "training_data": 14, "training_dev": 10, "training_imag": 7, "trajectori": 8, "transcendent": 8, "transcript": 16, "transfer": 11, "transform": [2, 3, 4, 5, 6, 7, 8, 9, 16, 17, 18, 19, 20, 22, 23, 24], "transformerblock": 15, "transit": 18, "translat": [3, 5, 6], "transpos": [1, 6], "treatment": 14, "tree": 16, "trigger": 14, "trigonometr": 8, "troubleshoot": 22, "true": [7, 8, 9, 10, 12, 13, 14], "true_label": 10, "truli": [2, 8, 10], "try": 24, "tune": [9, 10], "turn": [18, 22], "two": [4, 6, 12, 13], "txt": [17, 22], "type": [1, 4, 6, 7, 24], "typic": 5, "u": [8, 22], "uber": 14, "ultim": [], "unbound": 2, "unchang": [], "unclear": 19, "under": [11, 18, 20, 23], "underfit": 10, "underli": [], "understand": [0, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 18, 19, 21, 22], "understood": [19, 25], "unif": 25, "unifi": [16, 24], "uniform": 3, "unimpl": 17, "unimport": 11, "unit": [0, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 21], "uniti": [], "univers": [0, 4, 16, 18], "unlik": [6, 16], "unlock": [2, 16], "up": [5, 13, 17, 20, 22], "updat": [9, 14, 19, 22, 24], "upload": 17, "upon": [], "urgent": 17, "us": [15, 17, 19, 20, 21], "usabl": [], "usag": [7, 8, 11, 12, 13, 16, 18, 21], "user": [3, 4, 18, 25], "user_id": 14, "user_satisfact": 14, "util": [0, 1, 6, 7, 12, 19, 25], "v": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 18, 23, 25], "v2": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15], "v_": 9, "v_t": 9, "vae": 2, "val": 10, "val_acc": 10, "val_accuraci": 10, "val_dataload": 10, "val_dataset": 10, "val_load": [10, 14], "val_loss": 10, "valid": [0, 1, 2, 8, 9, 10, 11, 12, 17, 22, 24], "validate_input": 14, "validated_input": 14, "valu": [2, 6, 7, 8, 11, 17], "valuabl": 23, "vanish": [2, 3], "variabl": [8, 9, 13], "varianc": 25, "variant": [12, 14, 24], "variou": [2, 3, 4, 6], "ve": [6, 14, 23], "vector": [1, 3, 8, 19, 25], "vectorized_relu": 12, "vehicl": [5, 11, 14], "veloc": 9, "venv": [17, 22], "verbos": [10, 16], "verif": [12, 13, 14, 21], "verifi": [0, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 16, 21, 24], "version": [0, 2, 7, 12, 14, 17, 19, 25], "vertic": 16, "vgg": [2, 3, 4], "via": 17, "video": 1, "view": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16], "vijai": [18, 20], "violat": 14, "virtual": [6, 17, 24], "visibl": 19, "vision": [2, 3, 6, 7, 9, 10, 14, 15, 16, 17, 18, 20, 22, 23, 24], "visual": [6, 9, 10, 13, 17, 23, 24], "visualize_network_architectur": 4, "visualize_tinytorch_system": [], "vocabulari": 15, "voic": 9, "w": [1, 3], "w1": 9, "w2": 9, "wa": [16, 18], "wai": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 18, 19], "walk": 17, "walkthrough": 22, "want": [18, 23, 24], "warn": 21, "we": [1, 15, 18], "week": [17, 18, 22], "weekli": [14, 22], "weight": [3, 5, 6, 8, 11, 14, 18, 19, 22, 24, 25], "weight_dist": 11, "welcom": [0, 2], "well": [3, 5, 9], "what": [16, 19, 20, 22], "when": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 23, 25], "where": [1, 2, 3, 4, 6, 8, 9, 10, 12, 14, 16], "which": 17, "while": [11, 12, 20], "who": 19, "why": [2, 3, 5, 9, 15, 18, 23, 25], "wide": [4, 12], "wide_net": 4, "width": [4, 5], "wield": 15, "window": [5, 17, 19], "winner": [5, 13], "wise": [1, 2], "wish": 13, "within": [2, 3, 16], "without": [0, 1, 2, 6, 17, 23], "wonder": 25, "word": [3, 6], "work": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 17, 18, 20, 21, 22, 23, 25], "workaround": 25, "workflow": [18, 22, 23, 25], "workhors": 3, "workload": 12, "world": [21, 22, 24, 25], "would": [2, 18, 25], "wrap": 5, "wrapper": 8, "write": [0, 9], "wx": 3, "x": [1, 2, 3, 4, 5, 6, 8, 9, 11, 12, 13, 17, 18, 19, 21, 25], "xavier": 3, "xor": [18, 21], "xx_modul": 17, "xy": 8, "x\u00b2": [8, 9], "y": [1, 3, 8], "y_pred": 10, "y_true": 10, "yaml": [], "yang": 20, "yolo": 5, "yoshua": 20, "you": [15, 16, 17, 19, 20, 25], "your": [20, 21, 22, 23, 25], "your_trained_model": 13, "yourself": [5, 8, 9, 17, 18, 19], "z": [1, 8], "zero": [2, 3, 12, 19, 25], "zero_grad": [9, 19], "zero_point_a": 12, "zero_point_b": 12, "zero_point_correct": 12, "\u00b2": 9, "\u03b1": 9, "\u03b1v_": 9, "\u03b2v_t": 9, "\u03b8_": 9, "\u03b8_t": 9}, "titles": ["Module: Setup", "Module: Tensor", "Module: Activations", "Module: Layers", "Module: Networks", "Module: CNN", "Module: Attention", "Module: DataLoader", "Module: Autograd", "Module: Optimizers", "Module: Training", "Module: Compression", "Module: Kernels", "Module: Benchmarking", "Module: MLOps", "Module 16: TinyGPT - Language Models", "\ud83c\udfaf TinyTorch Checkpoint System", "\ud83d\udc68\u200d\ud83c\udfeb Instructor Guide: NBGrader + TinyTorch", "TinyTorch: Build Your Own ML Framework from First Principles", "KISS Principle in TinyTorch", "\ud83d\udcda Additional Learning Resources", "Testing Framework", "Classroom Use Overview", "Quick Exploration Path", "Serious Development Path", "The TinyTorch Vision"], "titleterms": {"": [7, 10], "0": 23, "00": 22, "02": 22, "03": 22, "07": 22, "08": 22, "1": [17, 18, 19, 21, 23, 24, 25], "10": 7, "11": 22, "12": 22, "15": 22, "16": [15, 16, 18, 22], "2": [17, 19, 21, 24, 25], "20": 0, "3": [17, 19, 21, 22, 23, 24, 25], "4": [17, 21, 23, 24, 25], "5": [17, 24], "6": [17, 24], "7": [17, 24], "8": 24, "A": 14, "For": [18, 25], "It": [18, 19], "One": 17, "The": [6, 16, 17, 18, 19, 24, 25], "Then": 23, "abstract": 7, "academ": [16, 20, 22], "acknowledg": 18, "action": [], "activ": [2, 3, 18, 23], "ad": 19, "addit": 20, "adopt": 22, "advanc": [4, 14, 17], "after": 16, "agent": 16, "ai": 6, "algorithm": [9, 25], "all": [18, 21], "altern": 20, "an": [22, 25], "analysi": [4, 9, 10, 11, 12], "analyz": [2, 5, 8, 13], "applic": [0, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14], "approach": [16, 24], "architectur": [4, 5, 10, 14, 15, 16, 21], "area": [2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14], "assess": 22, "assign": 17, "assur": 24, "attent": [6, 15], "audienc": 25, "auto": 17, "autograd": 8, "autom": [14, 16, 22], "automat": [8, 16], "b": 14, "base": 22, "batch": 17, "becom": 25, "befor": [19, 21], "benchmark": 13, "benefit": 19, "best": [4, 13, 17, 21], "beyond": 25, "block": [3, 5, 18, 22, 24], "book": 20, "build": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 18, 22, 23, 24, 25], "builder": 4, "built": 7, "capabl": 16, "capston": 14, "career": [18, 25], "chapter": 23, "characterist": 9, "check": [1, 16, 17], "checklist": 19, "checkpoint": [10, 16, 21], "choos": [22, 24], "cifar": 7, "clariti": 19, "class": [0, 1], "classroom": 22, "clear": 16, "cli": [16, 24], "clone": 17, "cnn": 5, "code": [19, 24], "cognit": 19, "collect": 17, "combin": 18, "command": [16, 17], "commit": 21, "common": 17, "commun": 22, "compact": 11, "comparison": 2, "complementari": [], "complet": [5, 7, 9, 10, 14, 16, 17, 18, 22], "complex": [19, 24], "compon": [15, 19], "composit": 4, "comprehens": [0, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 21, 22], "compress": 11, "comput": [5, 8], "concept": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14], "confid": 19, "configur": 17, "connect": [1, 18], "consider": [2, 7, 11], "construct": 8, "continu": 14, "contributor": 19, "converg": 9, "convolut": [5, 6], "core": [0, 1, 2, 3, 5, 9, 12, 15, 18], "cours": [17, 18, 20, 22], "coverag": [0, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14], "creat": 17, "criteria": 6, "curriculum": 22, "daili": 17, "data": [1, 7, 24], "dataload": 7, "dataset": 7, "debug": 19, "decis": 19, "deep": 20, "default": 19, "dens": 3, "depend": [], "deploi": 14, "deploy": [11, 16], "design": [4, 19], "detail": 5, "develop": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 16, 21, 24], "differ": [18, 25], "differenti": 8, "discov": [], "distil": 11, "distribut": 22, "dive": 20, "document": [19, 22], "dot": 6, "download": 7, "driven": 16, "dure": 21, "educ": [15, 19, 21, 25], "effici": [7, 11], "end": 17, "engag": [], "engin": [7, 10, 11, 12, 14, 20, 25], "enterpris": 14, "environ": [17, 24], "essenti": [1, 17], "estim": 15, "evalu": [10, 13], "exampl": [2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 18, 21], "excel": 22, "experi": 23, "experiment": 14, "explain": 6, "explicit": 19, "explor": 23, "export": [17, 24], "fail": 21, "featur": 22, "feedback": [16, 17, 22, 24], "file": [16, 19, 21], "first": [18, 25], "five": 16, "flexibl": 22, "formula": 6, "foundat": [0, 3, 8, 9, 16, 18, 20, 22, 24], "framework": [12, 13, 18, 19, 20, 21], "friendli": 22, "from": [6, 18], "function": [0, 2, 4, 10, 18], "fundament": [5, 12], "futur": 25, "galleri": [], "gener": [17, 18], "get": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 17, 22, 24], "goal": [7, 16], "govern": 14, "grade": [17, 22], "gradient": 2, "graph": 8, "guid": 17, "guidanc": 17, "guidelin": 19, "hardwar": 12, "health": 21, "help": [17, 24], "here": [16, 23], "how": 18, "hyperbol": 2, "i": 18, "immedi": [23, 24, 25], "impact": [18, 25], "implement": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 20], "implicit": 19, "import": 23, "indic": 21, "individu": 16, "industri": 22, "infer": 16, "info": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14], "inform": 0, "infrastructur": [14, 15, 22], "initi": 17, "inlin": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14], "insight": 15, "inspir": 13, "instal": 17, "instructor": [17, 22], "integr": [3, 8, 9, 10, 14, 16, 18, 21], "interact": [], "interfac": 19, "intern": 20, "interpret": 21, "introduct": [], "issu": 17, "journei": [16, 17, 18], "keep": 19, "kei": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15], "kernel": 12, "kiss": [19, 21], "knowledg": 11, "languag": [15, 16, 22], "launch": 23, "layer": [3, 23], "learn": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 18, 20, 22, 24, 25], "level": [21, 25], "librari": 10, "lifecycl": 14, "limit": 23, "linear": 2, "ll": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 18, 23, 24], "load": [7, 19], "loss": 10, "machin": [10, 20], "mainten": 17, "major": 16, "make": [15, 25], "manag": [14, 17], "manual": [1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13], "map": 16, "marker": 16, "mask": 6, "masteri": 25, "mathemat": [2, 3, 5, 8, 9], "matter": [1, 19], "mechan": 15, "memori": [1, 11], "methodologi": [12, 13], "metric": [10, 17, 22], "mid": 17, "minim": [19, 20], "minut": 24, "ml": [1, 7, 14, 18, 19, 25], "mlop": 14, "mlperf": 13, "model": [10, 11, 14, 15, 16, 22], "modern": 6, "modif": 19, "modul": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 21, 22, 24], "monitor": [14, 17], "nbgrader": 17, "network": [3, 4, 8], "neural": [3, 8, 16], "new": [7, 10], "next": [22, 23], "north": 7, "now": 18, "numer": 2, "object": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15], "observ": 14, "off": [19, 25], "one": [], "oper": [1, 5, 12, 17], "optim": [4, 7, 9, 10, 11, 12, 19], "option": 22, "organ": [19, 21], "outcom": [16, 22, 24, 25], "over": [16, 19], "overview": 22, "own": 18, "path": [23, 24], "pattern": [0, 3, 4, 5, 7, 8, 10, 11, 14, 21], "pedagog": [22, 25], "perfect": [18, 25], "perform": [1, 2, 7, 9, 12, 13, 19, 24], "phase": 17, "philosophi": [15, 18, 21, 25], "pipelin": [7, 10, 11], "plan": 17, "point": 22, "practic": [4, 13, 17, 19, 21], "prepar": [17, 22], "preprocess": 7, "prerequisit": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 15, 17, 18], "principl": [7, 18, 19, 21], "problem": 25, "process": [15, 17], "product": [6, 7, 11, 14, 18, 20, 22, 24], "profession": [13, 25], "profil": [0, 12], "program": 0, "progress": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 21, 24], "project": [14, 22], "promis": 19, "properti": 2, "proposit": 25, "proven": [22, 24], "prune": 11, "qualiti": 24, "quantiz": [11, 12], "quick": [17, 18, 21, 22, 23, 24], "rate": 9, "re": 25, "readi": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 18, 24, 25], "real": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 16, 24], "recognit": 22, "recommend": [17, 20, 23], "rectifi": 2, "reduct": 19, "refactor": 19, "refer": 17, "reflect": [0, 3, 18, 25], "releas": 17, "relev": 16, "relu": 2, "report": 13, "repositori": 17, "requir": 23, "resourc": [20, 22], "respons": 19, "result": [21, 24], "review": 19, "revolution": 6, "rich": 16, "right": 18, "roadmap": [], "routin": 17, "run": 21, "sai": 25, "save": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15], "scale": 6, "scenario": 13, "schedul": 9, "scratch": [], "self": 6, "semest": 17, "sequenti": 4, "seriou": 24, "serv": 14, "setup": [0, 17, 23, 24], "sigmoid": 2, "simd": 12, "simpl": 19, "singl": 19, "skill": 25, "solv": 25, "sparsiti": 11, "special": [4, 15], "stabil": 2, "star": 7, "start": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 16, 18, 21, 22, 23, 24], "statement": 16, "statist": 13, "statu": [17, 21], "step": [1, 17, 22, 23, 24], "stori": [22, 25], "structur": [1, 17], "student": [17, 22, 24, 25], "stupid": 19, "style": 19, "submiss": 17, "success": [6, 17, 22, 25], "suit": [0, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14], "support": [7, 22], "system": [0, 7, 8, 9, 10, 11, 13, 14, 16, 17, 18, 20, 21, 22, 24, 25], "tangent": 2, "tanh": 2, "target": 25, "task": 16, "tast": 18, "teach": [22, 25], "team": 16, "technic": 25, "techniqu": [11, 12], "tell": 17, "tensor": 1, "test": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 16, 21, 24], "testimoni": 22, "theori": [4, 8, 9, 20], "thi": [7, 10, 15, 16, 18, 24], "think": [16, 21, 25], "three": [], "time": [15, 17], "timelin": 16, "tini": [], "tinygpt": 15, "tinytorch": [0, 16, 17, 18, 19, 21, 22, 25], "tip": 17, "tito": 24, "tool": [10, 22], "torch": [], "track": 16, "trade": [19, 25], "tradit": [19, 25], "train": [9, 10, 15, 16, 18, 22, 24], "transform": [15, 25], "trigger": 19, "troubleshoot": [17, 21], "try": [18, 23], "understand": [1, 6, 17, 23, 24, 25], "uniqu": 25, "unit": 2, "univers": [1, 22], "up": 23, "us": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 16, 18, 22, 24, 25], "v": [6, 19], "valid": [7, 13, 14, 16, 21], "valu": [21, 25], "vector": 12, "verif": [1, 8], "verifi": 17, "vision": [5, 25], "visual": [2, 4, 5, 16], "wai": [], "we": [19, 25], "week": 24, "weekli": 17, "welcom": [], "what": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 17, 18, 23, 24, 25], "when": 19, "who": 18, "why": [1, 6, 16, 19, 22, 24], "work": [16, 24], "workflow": [0, 1, 2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 16, 17, 24], "world": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 16], "wrapper": 6, "you": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 18, 23, 24], "your": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 24], "yourself": []}}) |