Deep Spiking Networks

TL;DR

This paper presents a backpropagation algorithm for spiking neural networks that emulate traditional deep networks and performs well on MNIST, offering a promising approach for event-based streaming data processing.

Contribution

It introduces a novel backpropagation method for spiking networks that match the performance of conventional deep networks and are suitable for streaming data applications.

Findings

Spiking networks can replicate deep network behavior during training and prediction.

Achieved near-MLP performance on MNIST with a spiking architecture.

Network computation scales with the number of spikes, not network size.

Abstract

We introduce an algorithm to do backpropagation on a spiking network. Our network is "spiking" in the sense that our neurons accumulate their activation into a potential over time, and only send out a signal (a "spike") when this potential crosses a threshold and the neuron is reset. Neurons only update their states when receiving signals from other neurons. Total computation of the network thus scales with the number of spikes caused by an input rather than network size. We show that the spiking Multi-Layer Perceptron behaves identically, during both prediction and training, to a conventional deep network of rectified-linear units, in the limiting case where we run the spiking network for a long time. We apply this architecture to a conventional classification problem (MNIST) and achieve performance very close to that of a conventional Multi-Layer Perceptron with the same architecture. Our network is a natural architecture for learning based on streaming event-based data, and is a stepping stone towards using spiking neural networks to learn efficiently on streaming data.