Multi-Objective Optimization for Size and Resilience of Spiking Neural Networks

Mihaela Dimovska, Travis Johnston, Catherine D. Schuman, J. Parker Mitchell, Thomas E. Potok

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

12 Scopus citations

Abstract

Inspired by the connectivity mechanisms in the brain, neuromorphic computing architectures model Spiking Neural Networks (SNNs) in silicon. As such, neuromorphic architectures are designed and developed with the goal of having small, low power chips that can perform control and machine learning tasks. However, the power consumption of the developed hardware can greatly depend on the size of the network that is being evaluated on the chip. Furthermore, the accuracy of a trained SNN that is evaluated on chip can change due to voltage and current variations in the hardware that perturb the learned weights of the network. While efforts are made on the hardware side to minimize those perturbations, a software based strategy to make the deployed networks more resilient can help further alleviate that issue. In this work, we study Spiking Neural Networks in two neuromorphic architecture implementations with the goal of decreasing their size, while at the same time increasing their resiliency to hardware faults. We leverage an evolutionary algorithm to train the SNNs and propose a multiobjective fitness function to optimize the size and resiliency of the SNN. We demonstrate that this strategy leads to well-performing, small-sized networks that are more resilient to hardware faults.

Original languageEnglish
Title of host publication2019 IEEE 10th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference, UEMCON 2019
EditorsSatyajit Chakrabarti, Himadri Nath Saha
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages433-439
Number of pages7
ISBN (Electronic)9781728138855
DOIs
StatePublished - Oct 2019
Event10th IEEE Annual Ubiquitous Computing, Electronics and Mobile Communication Conference, UEMCON 2019 - New York City, United States
Duration: Oct 10 2019Oct 12 2019

Publication series

Name2019 IEEE 10th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference, UEMCON 2019

Conference

Conference10th IEEE Annual Ubiquitous Computing, Electronics and Mobile Communication Conference, UEMCON 2019
Country/TerritoryUnited States
CityNew York City
Period10/10/1910/12/19

Funding

This manuscript has been authored by UT-Battelle, LLC under Contract No. DE-AC05-00OR22725 with the U.S. Department of Energy. The United States Government retains and the publisher, by accepting the article for publication, acknowledges that the United States Government retains a non-exclusive, paid-up, irrevocable, worldwide license to publish or reproduce the published form of this manuscript, or allow others to do so, for United States Government purposes. The Department of Energy will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan (http://energy.gov/downloads/doe-public-access-plan).

FundersFunder number
U.S. Department of Energy
Office of Science
Advanced Scientific Computing ResearchDE-AC05-00OR22725
Oak Ridge National Laboratory

    Keywords

    • Evolutionary Optimization
    • Fault Tolerance
    • Multi-objective
    • Neuromorphic Computing
    • Spiking Neural Networks

    Fingerprint

    Dive into the research topics of 'Multi-Objective Optimization for Size and Resilience of Spiking Neural Networks'. Together they form a unique fingerprint.

    Cite this