Vijay Janapa Reddi 727da1cfcb fix(module-03): Rewrite Dropout to use Tensor operations ...

- Change from x.data * mask to Tensor multiplication (x * mask_tensor * scale)
- Preserves computation graph and gradient flow
- Required for transformer with dropout regularization

2025-10-27 20:29:43 -04:00

..

__init__.py

Fix nbdev export system across all 20 modules

2025-09-30 11:21:04 -04:00

activations.py

fix(module-02): Rewrite Softmax to use Tensor operations

2025-10-27 20:29:35 -04:00

attention.py

🤖 Fix transformer module exports and milestone 05 imports

2025-10-27 16:17:55 -04:00

autograd.py

feat: Add CrossEntropyLoss autograd support + Milestone 03 MLP on digits

2025-09-30 16:22:09 -04:00

layers.py

fix(module-03): Rewrite Dropout to use Tensor operations

2025-10-27 20:29:43 -04:00

losses.py

feat: Add CrossEntropyLoss autograd support + Milestone 03 MLP on digits

2025-09-30 16:22:09 -04:00

optimizers.py

Fix gradient propagation: enable autograd and patch activations/losses

2025-09-30 13:51:30 -04:00

optimizers.py.bak

Add milestone training examples and fix optimizers

2025-09-30 13:07:53 -04:00

spatial.py

feat: Add Milestone 04 (CNN Revolution 1998) + Clean spatial imports

2025-09-30 17:04:41 -04:00

tensor.py

fix(module-01): Fix batched matmul and transpose grad preservation

2025-10-27 20:28:53 -04:00

training.py

Reset package and export modules 01-07 only (skip broken spatial module)

2025-09-30 13:41:00 -04:00

training.py.bak

Add milestone training examples and fix optimizers

2025-09-30 13:07:53 -04:00