Evolutionary Optimization for Neuromorphic Systems

Catherine D. Schuman; J. Parker Mitchell; Robert M. Patton; Thomas E. Potok; James S. Plank

doi:10.1145/3381755.3381758

Evolutionary Optimization for Neuromorphic Systems

Catherine D. Schuman, J. Parker Mitchell, Robert M. Patton, Thomas E. Potok, James S. Plank

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

46 Scopus citations

Abstract

Designing and training an appropriate spiking neural network for neuromorphic deployment remains an open challenge in neuromorphic computing. In 2016, we introduced an approach for utilizing evolutionary optimization to address this challenge called Evolutionary Optimization for Neuromorphic Systems (EONS). In this work, we present an improvement to this approach that enables rapid prototyping of new applications of spiking neural networks in neuromorphic systems. We discuss the overall EONS framework and its improvements over the previous implementation. We present several case studies of how EONS can be used, including to train spiking neural networks for classification and control tasks, to train under hardware constraints, to evolve a reservoir for a liquid state machine, and to evolve smaller networks using multi-objective optimization.

Original language	English
Title of host publication	Proceedings of the 2020 Annual Neuro-Inspired Computational Elements Workshop, NICE 2020
Publisher	Association for Computing Machinery
ISBN (Electronic)	9781450361231
DOIs	https://doi.org/10.1145/3381755.3381758
State	Published - Mar 17 2020
Event	2020 Annual Neuro-Inspired Computational Elements Workshop, NICE 2020 - Heidelberg, Germany Duration: Mar 17 2020 → Mar 20 2020

Publication series

Name	ACM International Conference Proceeding Series

Conference

Conference	2020 Annual Neuro-Inspired Computational Elements Workshop, NICE 2020
Country/Territory	Germany
City	Heidelberg
Period	03/17/20 → 03/20/20

Funding

This material is based upon work supported by the U.S. Department of Energy, Office of Science, Office of Advanced Scientific Computing Research, under contract number DE-AC05-00OR22725, and by the Laboratory Directed Research and Development Program of Oak Ridge National Laboratory. Notice: This manuscript has been authored in part 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, world-wide 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).

Funders	Funder number
U.S. Department of Energy
Office of Science
Advanced Scientific Computing Research	DE-AC05-00OR22725
Oak Ridge National Laboratory

Keywords

genetic algorithms
neuromorphic computing
spiking neural networks

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1145/3381755.3381758

Cite this

@inproceedings{c0c62aca65c04bb390d1ab62c5995cbc,

title = "Evolutionary Optimization for Neuromorphic Systems",

abstract = "Designing and training an appropriate spiking neural network for neuromorphic deployment remains an open challenge in neuromorphic computing. In 2016, we introduced an approach for utilizing evolutionary optimization to address this challenge called Evolutionary Optimization for Neuromorphic Systems (EONS). In this work, we present an improvement to this approach that enables rapid prototyping of new applications of spiking neural networks in neuromorphic systems. We discuss the overall EONS framework and its improvements over the previous implementation. We present several case studies of how EONS can be used, including to train spiking neural networks for classification and control tasks, to train under hardware constraints, to evolve a reservoir for a liquid state machine, and to evolve smaller networks using multi-objective optimization.",

keywords = "genetic algorithms, neuromorphic computing, spiking neural networks",

author = "Schuman, {Catherine D.} and Mitchell, {J. Parker} and Patton, {Robert M.} and Potok, {Thomas E.} and Plank, {James S.}",

note = "Publisher Copyright: {\textcopyright} 2020 ACM.; 2020 Annual Neuro-Inspired Computational Elements Workshop, NICE 2020 ; Conference date: 17-03-2020 Through 20-03-2020",

year = "2020",

month = mar,

day = "17",

doi = "10.1145/3381755.3381758",

language = "English",

series = "ACM International Conference Proceeding Series",

publisher = "Association for Computing Machinery",

booktitle = "Proceedings of the 2020 Annual Neuro-Inspired Computational Elements Workshop, NICE 2020",

}

Schuman, CD, Mitchell, JP, Patton, RM , Potok, TE & Plank, JS 2020, Evolutionary Optimization for Neuromorphic Systems. in Proceedings of the 2020 Annual Neuro-Inspired Computational Elements Workshop, NICE 2020. ACM International Conference Proceeding Series, Association for Computing Machinery, 2020 Annual Neuro-Inspired Computational Elements Workshop, NICE 2020, Heidelberg, Germany, 03/17/20. https://doi.org/10.1145/3381755.3381758

Evolutionary Optimization for Neuromorphic Systems. / Schuman, Catherine D.; Mitchell, J. Parker; Patton, Robert M. et al.
Proceedings of the 2020 Annual Neuro-Inspired Computational Elements Workshop, NICE 2020. Association for Computing Machinery, 2020. (ACM International Conference Proceeding Series).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Evolutionary Optimization for Neuromorphic Systems

AU - Schuman, Catherine D.

AU - Mitchell, J. Parker

AU - Patton, Robert M.

AU - Potok, Thomas E.

AU - Plank, James S.

PY - 2020/3/17

Y1 - 2020/3/17

N2 - Designing and training an appropriate spiking neural network for neuromorphic deployment remains an open challenge in neuromorphic computing. In 2016, we introduced an approach for utilizing evolutionary optimization to address this challenge called Evolutionary Optimization for Neuromorphic Systems (EONS). In this work, we present an improvement to this approach that enables rapid prototyping of new applications of spiking neural networks in neuromorphic systems. We discuss the overall EONS framework and its improvements over the previous implementation. We present several case studies of how EONS can be used, including to train spiking neural networks for classification and control tasks, to train under hardware constraints, to evolve a reservoir for a liquid state machine, and to evolve smaller networks using multi-objective optimization.

AB - Designing and training an appropriate spiking neural network for neuromorphic deployment remains an open challenge in neuromorphic computing. In 2016, we introduced an approach for utilizing evolutionary optimization to address this challenge called Evolutionary Optimization for Neuromorphic Systems (EONS). In this work, we present an improvement to this approach that enables rapid prototyping of new applications of spiking neural networks in neuromorphic systems. We discuss the overall EONS framework and its improvements over the previous implementation. We present several case studies of how EONS can be used, including to train spiking neural networks for classification and control tasks, to train under hardware constraints, to evolve a reservoir for a liquid state machine, and to evolve smaller networks using multi-objective optimization.

KW - genetic algorithms

KW - neuromorphic computing

KW - spiking neural networks

UR - http://www.scopus.com/inward/record.url?scp=85123040518&partnerID=8YFLogxK

U2 - 10.1145/3381755.3381758

DO - 10.1145/3381755.3381758

M3 - Conference contribution

AN - SCOPUS:85123040518

T3 - ACM International Conference Proceeding Series

BT - Proceedings of the 2020 Annual Neuro-Inspired Computational Elements Workshop, NICE 2020

PB - Association for Computing Machinery

T2 - 2020 Annual Neuro-Inspired Computational Elements Workshop, NICE 2020

Y2 - 17 March 2020 through 20 March 2020

ER -

Evolutionary Optimization for Neuromorphic Systems

Abstract

Publication series

Conference

Funding

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this