Practical PyTorch for event-based computing

This session consists of two parts: a whirlwind introduction to PyTorch and its use in neuromorphics.

The first part (20 minutes) will explain the fundamentals of PyTorch by

• How PyTorch works with tensors and network layers


• How PyTorch propagates gradients


• How PyTorch can optimize networks

The second part (30 minutes) will explain how we can use PyTorch in neuromorphics by

• Introducing spiking simulations via the PyTorch extension Norse (github.com/norse/norse)


• Connecting to event cameras with AEStream (github.com/aestream/aestream)


• Real-time edge detection of event data with an SNN

Go to group wiki Go to wiki users Info

Timetable

Moderator

Member