mirror of
https://github.com/MLSysBook/TinyTorch.git
synced 2026-05-04 11:33:05 -05:00
6491a7512e
- Removed temporary test files and audit reports - Deleted backup and temp_holding directories - Reorganized module structure (07->09 spatial, 09->07 dataloader) - Added new modules: 11-14 (tokenization, embeddings, attention, transformers) - Updated examples with historical ML milestones - Cleaned up documentation structure
21 lines
768 B
YAML
21 lines
768 B
YAML
name: "Loss Functions"
|
|
number: 5
|
|
description: "Essential loss functions for neural network training objectives"
|
|
learning_objectives:
|
|
- "Implement MSE, CrossEntropy, and BinaryCrossEntropy loss functions"
|
|
- "Understand numerical stability in loss computation"
|
|
- "Match loss functions to problem types (regression vs classification)"
|
|
- "Build production-ready loss functions with batch processing"
|
|
prerequisites:
|
|
- "02_tensor"
|
|
difficulty: "⭐⭐⭐"
|
|
time_estimate: "2-3 hours"
|
|
exports:
|
|
- "MeanSquaredError"
|
|
- "CrossEntropyLoss"
|
|
- "BinaryCrossEntropyLoss"
|
|
key_concepts:
|
|
- "Training objectives and optimization"
|
|
- "Numerical stability in loss computation"
|
|
- "Regression vs classification loss functions"
|
|
- "Batch processing for scalable training" |