snntorch
snntorch copied to clipboard
Mixed-mode autodiff for RTRL
- Implement forward-mode AD for temporal connections; reverse-mode AD for layer connections
- Update at each time step
- Approximate BPTT without having to store any historical gradients
Willing to work on this. Could you give some more details please ?
@saiftyfirst , like this
https://pytorch.org/tutorials//intermediate/forward_ad_usage.html?highlight=func