Vijay Janapa Reddi d05daeb83b Add comprehensive milestone learning verification tests ...

- Created test suite that verifies actual learning (gradient flow, weight updates, loss convergence)
- Fixed MLP Digits (1986): increased training epochs from 15 to 25
- Added requires_grad=True to Conv2d weights (partial fix)
- Identified gradient flow issues in Conv2d, Embedding, and Attention layers
- Comprehensive documentation of issues and fixes needed

2025-11-22 17:02:10 -05:00

..

__init__.py

Fix nbdev export system across all 20 modules

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

activations.py

Update tinytorch and tito with module exports

2025-11-10 19:42:03 -05:00

attention.py

Update tinytorch and tito with module exports

2025-11-10 19:42:03 -05:00

autograd.py

Fix duplicate autograd enabled messages

2025-11-22 15:31:39 -05:00

layers.py

Update tinytorch and tito with module exports

2025-11-10 19:42:03 -05:00

losses.py

Update tinytorch and tito with module exports

2025-11-10 19:42:03 -05:00

optimizers.py

Update tinytorch and tito with module exports

2025-11-10 19:42:03 -05:00

spatial.py

Add comprehensive milestone learning verification tests

2025-11-22 17:02:10 -05:00

tensor.py

Update tinytorch and tito with module exports

2025-11-10 19:42:03 -05:00

training.py

Update tinytorch and tito with module exports

2025-11-10 19:42:03 -05:00