# SuperSpike: Supervised learning in multi-layer spiking neural networks

## TL;DR

SuperSpike introduces a novel supervised learning rule for multi-layer spiking neural networks, enabling them to perform complex nonlinear computations on spatiotemporal spike patterns, advancing understanding of biological and artificial neural learning.

## Contribution

The paper develops SuperSpike, a surrogate gradient-based nonlinear voltage-dependent learning rule for training multi-layer spiking neural networks with different feedback strategies.

## Key findings

- SuperSpike effectively trains multi-layer spiking networks for nonlinear tasks.
- Symmetric feedback is necessary for complex tasks.
- Different feedback strategies impact learning success depending on task complexity.

## Abstract

A vast majority of computation in the brain is performed by spiking neural networks. Despite the ubiquity of such spiking, we currently lack an understanding of how biological spiking neural circuits learn and compute in-vivo, as well as how we can instantiate such capabilities in artificial spiking circuits in-silico. Here we revisit the problem of supervised learning in temporally coding multi-layer spiking neural networks. First, by using a surrogate gradient approach, we derive SuperSpike, a nonlinear voltage-based three factor learning rule capable of training multi-layer networks of deterministic integrate-and-fire neurons to perform nonlinear computations on spatiotemporal spike patterns. Second, inspired by recent results on feedback alignment, we compare the performance of our learning rule under different credit assignment strategies for propagating output errors to hidden units. Specifically, we test uniform, symmetric and random feedback, finding that simpler tasks can be solved with any type of feedback, while more complex tasks require symmetric feedback. In summary, our results open the door to obtaining a better scientific understanding of learning and computation in spiking neural networks by advancing our ability to train them to solve nonlinear problems involving transformations between different spatiotemporal spike-time patterns.