4. Neuromorphic hardware

We have seen how we can compute with spikes in the spatial and temporal domain. We also saw how sensors can provide us with spiking data and how we can work with that using our newfound knowledge about neurons and computation. Now, we will see how neuromorphic hardware can integrate with event sensors and how they allow us to compute efficiently on the event-based framework.

Lecture content

1. Working with Speck

2. Project 4: Classification task on speck

Literature

• Training Spiking Neural Networks Using Lessons From Deep Learning

• SuperSpike: Supervised Learning in Multilayer Spiking Neural Networks

• Translation and Scale Invariance for Event-Based Object tracking