Vijay Janapa Reddi 06b35c34bd Fix training pipeline: Parameter class, Variable.sum(), gradient handling ...

Major fixes for complete training pipeline functionality:

Core Components Fixed:
- Parameter class: Now wraps Variables with requires_grad=True for proper gradient tracking
- Variable.sum(): Essential for scalar loss computation from multi-element tensors
- Gradient handling: Fixed memoryview issues in autograd and activations
- Tensor indexing: Added __getitem__ support for weight inspection

Training Results:
- XOR learning: 100% accuracy (4/4) - network successfully learns XOR function
- Linear regression: Weight=1.991 (target=2.0), Bias=0.980 (target=1.0)
- Integration tests: 21/22 passing (95.5% success rate)
- Module tests: All individual modules passing
- General functionality: 4/5 tests passing with core training working

Technical Details:
- Fixed gradient data access patterns throughout activations.py
- Added safe memoryview handling in Variable.backward()
- Implemented proper Parameter-Variable delegation
- Added Tensor subscripting for debugging access(https://claude.ai/code)

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

..

commands

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

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

core

Fix: Restore proper hierarchical CLI structure and fix config

2025-09-28 07:15:25 -04:00

tools

Implement logical test sequencing - unit tests run first, then integration tests

2025-07-20 13:02:21 -04:00

__init__.py

MAJOR: Separate CLI from framework - proper architectural separation

2025-07-10 22:08:56 -04:00

main.py

Implement clean start/resume/complete workflow - no overlaps!

2025-09-28 07:58:06 -04:00