This commit introduces the core building blocks for neural networks,
including a naive matrix multiplication implementation and a Dense layer.
It provides a foundation for constructing and experimenting with
neural networks, emphasizing the concept of layers as tensor
transformations and function composition.
The module includes thorough testing and performance comparisons
to demonstrate the importance of optimized operations.
- Add template section to tensor, layers, activations, and cnn modules
- Create docs/development/module-template.md for future reference
- Clarify learning vs building structure consistently
- Show students where their code will live in the final package
- Decouple learning modules from production organization
- Add matmul_naive function with for-loop implementation for learning
- Update Dense layer to support both NumPy (@) and naive matrix multiplication
- Add comprehensive tests comparing both implementations (correctness & performance)
- Include step-by-step computation visualization for 2x2 matrices
- Fix missing imports in tensor.py and activations.py
- Export both tensor and activations modules to package
This provides students with immediate success using NumPy while allowing them to
understand the underlying computation through explicit for-loops. The scaffolding
includes performance comparisons and educational insights about why NumPy is faster.
��️ Major architectural improvement implementing clean separation of concerns:
✨ NEW: Activations Module
- Complete activations module with ReLU, Sigmoid, Tanh implementations
- Educational NBDev structure with student TODOs + instructor solutions
- Comprehensive testing suite (24 tests) with mathematical correctness validation
- Visual learning features with matplotlib plotting (disabled during testing)
- Clean export to tinytorch.core.activations
🔧 REFACTOR: Layers Module
- Removed duplicate activation function implementations
- Clean import from activations module: 'from tinytorch.core.activations import ReLU, Sigmoid, Tanh'
- Updated documentation to reflect modular architecture
- Preserved all existing functionality while improving code organization
🧪 TESTING: Comprehensive Test Coverage
- All 24 activations tests passing ✅
- All 17 layers tests passing ✅
- Integration tests verify clean architecture works end-to-end
- CLI testing with 'tito test --module' works for both modules
📦 ARCHITECTURE: Clean Dependency Graph
- activations (math functions) → layers (building blocks) → networks (applications)
- Separation of concerns: pure math vs. neural network components
- Reusable components across future modules
- Single source of truth for activation implementations
�� PEDAGOGY: Enhanced Learning Experience
- Week-sized chunks: students master activations, then build layers
- Clear progression from mathematical foundations to applications
- Real-world software architecture patterns
- Modular design principles in practice
This establishes the foundation for scalable, maintainable ML systems education.
✨ Features:
- Dense layer with Xavier initialization (y = Wx + b)
- Activation functions: ReLU, Sigmoid, Tanh
- Layer composition for building neural networks
- Comprehensive test suite (17 passed, 5 skipped stretch goals)
- Package-level integration tests (14 passed)
- Complete documentation and examples
🎯 Educational Design:
- Follows 'Build → Use → Understand' pedagogical framework
- Immediate visual feedback with working examples
- Progressive complexity from simple layers to full networks
- Students see neural networks as function composition
🧪 Testing Architecture:
- Module tests: 17/17 core tests pass, 5 stretch goals available
- Package tests: 14/14 integration tests pass
- Dual testing supports both learning and validation
📚 Complete Implementation:
- Dense layer with proper weight initialization
- Numerically stable activation functions
- Batch processing support
- Real-world examples (image classification network)
- CLI integration: 'tito test --module layers'
This establishes the fundamental building blocks students need
to understand neural networks before diving into training.
