mirror of
https://github.com/MLSysBook/TinyTorch.git
synced 2026-06-05 01:33:45 -05:00
48e62a954a
- Changed all module titles to be short and clean (e.g., 'Autograd' not 'Autograd - Automatic Differentiation') - Updated metadata generation template to use concise titles by default - Fixed CLI reference in metadata generator to use new hierarchical structure - Titles are now consistent: just the module name capitalized - Detailed descriptions remain in the description field where they belong
97 lines
2.7 KiB
YAML
97 lines
2.7 KiB
YAML
# TinyTorch Module Metadata
|
|
# This file contains structured information about the module for CLI tools and documentation
|
|
|
|
# Basic Information
|
|
name: "layers"
|
|
title: "Layers"
|
|
description: "Build the fundamental transformations that compose into neural networks - Dense layers and activation functions"
|
|
version: "1.0.0"
|
|
author: "TinyTorch Team"
|
|
last_updated: "2024-12-19"
|
|
|
|
# Module Status
|
|
status: "complete" # complete, in_progress, not_started, deprecated
|
|
implementation_status: "stable" # stable, beta, alpha, experimental
|
|
|
|
# Learning Information
|
|
learning_objectives:
|
|
- "Understand layers as functions that transform tensors: y = f(x)"
|
|
- "Implement Dense layers with linear transformations: y = Wx + b"
|
|
- "Add activation functions for nonlinearity (ReLU, Sigmoid, Tanh)"
|
|
- "See how neural networks are just function composition"
|
|
- "Build intuition for neural network architecture before diving into training"
|
|
|
|
key_concepts:
|
|
- "Linear transformations"
|
|
- "Weight matrices and biases"
|
|
- "Function composition"
|
|
- "Layer abstraction"
|
|
- "Neural network building blocks"
|
|
|
|
# Dependencies
|
|
dependencies:
|
|
prerequisites: ["setup", "tensor", "activations"]
|
|
builds_on: ["tensor", "activations"]
|
|
enables: ["networks", "training"]
|
|
|
|
# Educational Metadata
|
|
difficulty: "intermediate" # beginner, intermediate, advanced
|
|
estimated_time: "3-4 hours"
|
|
pedagogical_pattern: "Build → Use → Understand"
|
|
|
|
# Implementation Details
|
|
components:
|
|
- name: "Dense"
|
|
type: "class"
|
|
description: "Linear transformation layer: y = Wx + b"
|
|
status: "complete"
|
|
|
|
- name: "Layer"
|
|
type: "base_class"
|
|
description: "Abstract base class for all layers"
|
|
status: "complete"
|
|
|
|
# Package Export Information
|
|
exports_to: "tinytorch.core.layers"
|
|
export_directive: "core.layers"
|
|
|
|
# Testing Information
|
|
test_coverage: "comprehensive" # comprehensive, partial, minimal, none
|
|
test_count: 15
|
|
test_categories:
|
|
- "Dense layer construction"
|
|
- "Forward pass computation"
|
|
- "Shape transformations"
|
|
- "Weight initialization"
|
|
- "Bias handling"
|
|
- "Composition with activations"
|
|
|
|
# File Structure
|
|
required_files:
|
|
- "layers_dev.py"
|
|
- "layers_dev.ipynb"
|
|
- "tests/test_layers.py"
|
|
- "README.md"
|
|
|
|
# Systems Focus
|
|
systems_concepts:
|
|
- "Modular design"
|
|
- "Object-oriented programming"
|
|
- "Function composition"
|
|
- "Memory management"
|
|
- "Numerical stability"
|
|
|
|
# Real-world Applications
|
|
applications:
|
|
- "Multi-layer perceptrons"
|
|
- "Deep neural networks"
|
|
- "Feature extraction"
|
|
- "Representation learning"
|
|
|
|
# Next Steps
|
|
next_modules: ["networks", "training"]
|
|
completion_criteria:
|
|
- "All tests pass"
|
|
- "Can build 2-layer neural network"
|
|
- "Understand layer composition"
|
|
- "Ready for network architectures" |