Learning First-to-Spike Policies for Neuromorphic Control Using Policy Gradients

Bleema Rosenfeld, Osvaldo Simeone, Bipin Rajendran

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Scopus citations

Abstract

Artificial Neural Networks (ANNs) are currently being used as function approximators in many state-of-the-art Reinforcement Learning (RL) algorithms. Spiking Neural Networks (SNNs) have been shown to drastically reduce the energy consumption of ANNs by encoding information in sparse temporal binary spike streams, hence emulating the communication mechanism of biological neurons. Due to their low energy consumption, SNNs are considered to be important candidates as co-processors to be implemented in mobile devices. In this work, the use of SNNs as stochastic policies is explored under an energy-efficient first-to-spike action rule, whereby the action taken by the RL agent is determined by the occurrence of the first spike among the output neurons. A policy gradient-based algorithm is derived considering a Generalized Linear Model (GLM) for spiking neurons. Experimental results demonstrate the capability of online trained SNNs as stochastic policies to gracefully trade energy consumption, as measured by the number of spikes, and control performance. Significant gains are shown as compared to the standard approach of converting an offline trained ANN into an SNN.

Original languageEnglish (US)
Title of host publication2019 IEEE 20th International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538665282
DOIs
StatePublished - Jul 2019
Event20th IEEE International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2019 - Cannes, France
Duration: Jul 2 2019Jul 5 2019

Publication series

NameIEEE Workshop on Signal Processing Advances in Wireless Communications, SPAWC
Volume2019-July

Conference

Conference20th IEEE International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2019
Country/TerritoryFrance
CityCannes
Period7/2/197/5/19

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering
  • Computer Science Applications
  • Information Systems

Keywords

  • Neuromorphic Computing
  • Policy Gradient
  • Reinforcement Learning
  • Spiking Neural Network

Fingerprint

Dive into the research topics of 'Learning First-to-Spike Policies for Neuromorphic Control Using Policy Gradients'. Together they form a unique fingerprint.

Cite this