Intermediate · Neural networks from scratch
An autograd engine
Build an engine that works out gradients by itself, as PyTorch's autograd does: values and arrays that remember how they were made, a backward pass in topological order, broadcasting summed back, and gradients that match PyTorch's on random expressions.
- You build
- engine.py, then autograd.py
- Stages
- 3 Build, 1 Catch, 1 Ship
- Time
- About 4.5 hours
Loading the workspace…
Loading the workspace…