Vijay Janapa Reddi 6f0c96c130 Fix gradient flow with PyTorch-style requires_grad tracking ...

- Updated Linear layer to use autograd operations (matmul, add) for proper gradient propagation
- Fixed Parameter class to wrap Variables with requires_grad=True
- Implemented proper MSELoss and CrossEntropyLoss with backward chaining
- Added broadcasting support in autograd operations for bias gradients
- Fixed memoryview errors in gradient data extraction
- All integration tests now pass - neural networks can learn via backpropagation

2025-09-29 10:46:58 -04:00

..

__init__.py

FEAT: Complete optimization modules 15-20 with ML Systems focus

2025-09-24 22:34:20 -04:00

_import_guard.py

feat: Implement comprehensive student protection system for TinyTorch

2025-09-21 12:22:18 -04:00

_validation.py

Add advanced CIFAR-10 optimization and universal dashboard

2025-09-21 16:53:27 -04:00

activations.py

Fix training pipeline: Parameter class, Variable.sum(), gradient handling

2025-09-28 19:14:11 -04:00

attention.py

FEAT: Complete optimization modules 15-20 with ML Systems focus

2025-09-24 22:34:20 -04:00

autograd.py

Fix gradient flow with PyTorch-style requires_grad tracking

2025-09-29 10:46:58 -04:00

cnn.py

🔧 Complete module restructuring and integration fixes

2025-07-18 02:10:49 -04:00

dataloader.py

Complete comprehensive system validation and cleanup

2025-09-23 10:00:33 -04:00

dense.py

Complete comprehensive system validation and cleanup

2025-09-23 10:00:33 -04:00

embeddings.py

Clean up repository: remove temp files, organize modules, prepare for PyPI publication

2025-09-24 10:13:37 -04:00

kernels.py

Complete comprehensive system validation and cleanup

2025-09-23 10:00:33 -04:00

layers.py

Fix gradient flow with PyTorch-style requires_grad tracking

2025-09-29 10:46:58 -04:00

losses.py

Fix gradient flow with PyTorch-style requires_grad tracking

2025-09-29 10:46:58 -04:00

mlops.py

Complete comprehensive system validation and cleanup

2025-09-23 10:00:33 -04:00

networks.py

FEAT: Complete performance validation and optimization fixes

2025-09-25 14:57:35 -04:00

optimizers.py

Fix training pipeline: Parameter class, Variable.sum(), gradient handling

2025-09-28 19:14:11 -04:00

spatial_dev.py

FEAT: Complete performance validation and optimization fixes

2025-09-25 14:57:35 -04:00

spatial.py

FEAT: Complete performance validation and optimization fixes

2025-09-25 14:57:35 -04:00

tensor.py

Fix training pipeline: Parameter class, Variable.sum(), gradient handling

2025-09-28 19:14:11 -04:00

training.py

CRITICAL FIX: Remove forward dependencies violating learning progression

2025-09-23 19:13:11 -04:00

transformers.py

Clean up repository: remove temp files, organize modules, prepare for PyPI publication

2025-09-24 10:13:37 -04:00