Long Short-Term Memory Spiking Networks and Their Applications

TL;DR

This paper introduces a novel training framework for recurrent spiking neural networks based on LSTM architectures, enabling them to learn long-term dependencies effectively, bridging the gap with traditional LSTMs.

Contribution

It presents a new methodology for training LSTM-based spiking neural networks, addressing the challenge of learning temporal dependencies in neuromorphic systems.

Findings

LSTM spiking networks learn spike timing and temporal dependencies.

The proposed backpropagation method enables learning long-term dependencies.

Performance comparable to conventional LSTMs on temporal tasks.

Abstract

Recent advances in event-based neuromorphic systems have resulted in significant interest in the use and development of spiking neural networks (SNNs). However, the non-differentiable nature of spiking neurons makes SNNs incompatible with conventional backpropagation techniques. In spite of the significant progress made in training conventional deep neural networks (DNNs), training methods for SNNs still remain relatively poorly understood. In this paper, we present a novel framework for training recurrent SNNs. Analogous to the benefits presented by recurrent neural networks (RNNs) in learning time series models within DNNs, we develop SNNs based on long short-term memory (LSTM) networks. We show that LSTM spiking networks learn the timing of the spikes and temporal dependencies. We also develop a methodology for error backpropagation within LSTM-based SNNs. The developed architecture and method for backpropagation within LSTM-based SNNs enable them to learn long-term dependencies with comparable results to conventional LSTMs.