research-article

Evolutionary Optimization for Neuromorphic Systems

Authors:

Catherine D. Schuman,

J. Parker Mitchell,

Robert M. Patton,

Thomas E. Potok,

James S. PlankAuthors Info & Claims

NICE '20: Proceedings of the 2020 Annual Neuro-Inspired Computational Elements Workshop

Article No.: 2, Pages 1 - 9

https://doi.org/10.1145/3381755.3381758

Published: 18 June 2020 Publication History

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.

References

[1]

S.M. Bohte, J.N. Kok, and J.A. La Poutré. 2000. SpikeProp: backpropagation for networks of spiking neurons. In ESANN. 419--424.

[2]

G. Brockman, V. Cheung, L. Pettersson, J. Schneider, J. Schulman, J. Tang, and W. Zaremba. 2016. Openai gym. arXiv preprint arXiv:1606.01540 (2016).

[3]

S. Buckley, A. N. McCaughan, J. Chiles, R. P. Mirin, S. W. Nam, J. M. Shainline, G. Bruer, J. S. Plank, and C. D. Schuman. 2018. Design of superconducting optoelectronic networks for neuromorphic computing. In IEEE International Conference on Rebooting Computing. Tysons, VA, 36--42.

[4]

S. Cawley, F. Morgan, B. McGinley, S. Pande, L. McDaid, S. Carrillo, and J. Harkin. 2011. Hardware spiking neural network prototyping and application. Genetic Programming and Evolvable Machines 12, 3 (2011), 257--280.

Digital Library

[5]

G. Chakma, N. D. Skuda, C. D. Schuman, J. S. Plank, M. E. Dean, and G. S. Rose. 2018. Energy and Area Efficiency in Neuromorphic Computing for Resource Constrained Devices. In Proceedings of ACM Great Lake Symposium on VLSI (GLSVLSI). Chicago, IL, 379--383.

[6]

M. Davies et al. 2018. Loihi: A Neuromorphic Manycore Processor with On-Chip Learning. IEEE Micro 38, 1 (2018), 82--99.

[7]

Peter U Diehl, Guido Zarrella, Andrew Cassidy, Bruno U Pedroni, and Emre Neftci. 2016. Conversion of artificial recurrent neural networks to spiking neural networks for low-power neuromorphic hardware. In 2016 IEEE International Conference on Rebooting Computing (ICRC). IEEE, 1--8.

[8]

Mihaela Dimovska, J. Travis Johnston, Catherine D. Schuman, J. Parker Mitchell, and Thomas E. Potok. 2019. Multi-Objective Optimization for Size and Resilience of Spiking Neural Networks. In 2019 IEEE Annual Ubiquitous Computing, Electronics, and Mobile Communication Conference. IEEE, In press.

[9]

A.Disney, J. Reynolds, C.D. Schuman, A. Klibisz, A. Young, and J. S. Plank. 2016. DANNA: A Neuromorphic Software Ecosystem. Biologically Inspired Cognitive Architectures 9 (July 2016), 49--56.

[10]

A. W. Disney, J. S. Plank, and M. Dean. 2018. Four Simulators of the DANNA Neuromorphic Computing Architecture. In International Conference on Neuromorphic Computing Systems. ACM, Knoxville, TN.

[11]

Chao Du, Fuxi Cai, Mohammed A Zidan, Wen Ma, Seung Hwan Lee, and Wei D Lu. 2017. Reservoir computing using dynamic memristors for temporal information processing. Nature communications 8, 1 (2017), 2204.

[12]

Steve K Esser, Rathinakumar Appuswamy, Paul Merolla, John V Arthur, and Dharmendra S Modha. 2015. Backpropagation for energy-efficient neuromorphic computing. In Advances in Neural Information Processing Systems. 1117--1125.

[13]

P. Ferré, F. Mamalet, and S.J. Thorpe. [n.d.]. Unsupervised feature learning with winner-takes-all based STDP. Frontiers in computational neuroscience 12 ([n. d.]).

[14]

Dario Floreano, Peter Dürr, and Claudio Mattiussi. 2008. Neuroevolution: from architectures to learning. Evolutionary intelligence 1, 1 (2008), 47--62.

[15]

F. Gomez, J. Schmidhuber, and R. Miikkulainen. 2008. Accelerated neural evolution through cooperatively coevolved synapses. Journal of Machine Learning Research 9, May (2008), 937--965.

Digital Library

[16]

M. S. Hasan, C. D. Schuman, J. S. Najem, R. Weiss, N. D. Skuda, A. Belianinov, C. P. Collier, S. A. Sarles, and G. S. Rose. 2018. Biomimetic, Soft-Material Synapse for Neuromorphic Computing: From Device to Network. In IEEE 13th Dallas Circuits and Systems Conference (DCAS). https://doi.org/10.1109/DCAS.2018.8620187

[17]

N. Kasabov, V. Feigin, Z. Hou, Y. Chen, L. Liang, R. Krishnamurthi, M. Othman, and P. Parmar. 2014. Evolving spiking neural networks for personalised modelling, classification and prediction of spatio-temporal patterns with a case study on stroke. Neurocomputing 134 (2014), 269--279.

Digital Library

[18]

E. Kim, J. Yarnall, P. Shaha, and G. T. Kenyon. 2019. A Neuromorphic Sparse Coding Defense to Adversarial Images., 8 pages.

[19]

Dhireesha Kudithipudi, Qutaiba Saleh, Cory Merkel, James Thesing, and Bryant Wysocki. 2016. Design and analysis of a neuromemristive reservoir computing architecture for biosignal processing. Frontiers in neuroscience 9 (2016), 502.

[20]

Jun Haeng Lee, Tobi Delbruck, and Michael Pfeiffer. 2016. Training deep spiking neural networks using backpropagation. Frontiers in neuroscience 10 (2016), 508.

[21]

R. Miikkulainen, J. Liang, E. Meyerson, A. Rawal, D. Fink, O. Francon, B. Raju, H. Shahrzad, A. Navruzyan, N. Duffy, et al. 2019. Evolving deep neural networks. In Artificial Intelligence in the Age of Neural Networks and Brain Computing. Elsevier, 293--312.

[22]

J. Parker Mitchell, Catherine D. Schuman, Robert M. Patton, and Thomas E. Potok. 2019. Caspian: A Neuromorphic Development Platform. In Submitted.

[23]

J. S. Plank, C. Rizzo, K. Shahat, G. Bruer, T. Dixon, M. Goin, G. Zhao, J. Anantharaj, C. D. Schuman, M. E. Dean, G. S. Rose, N. C. Cady, and J. Van Nostrand. 2019. The TENNLab Suite of LIDAR-Based Control Applications for Recurrent, Spiking, Neuromorphic Systems. In 44th Annual GOMACTech Conference. Albuquerque.

[24]

James S Plank, Catherine D Schuman, Grant Bruer, Mark E Dean, and Garrett S Rose. 2018. The TENNLab exploratory neuromorphic computing framework. IEEE Letters of the Computer Society 1, 2 (2018), 17--20.

[25]

Anvesh Polepalli, Nicholas Soures, and Dhireesha Kudithipudi. 2016. Digital neuromorphic design of a liquid state machine for real-time processing. In 2016 IEEE International Conference on Rebooting Computing (ICRC). IEEE, 1--8.

[26]

Daniel Rasmussen. 2019. NengoDL: Combining deep learning and neuromorphic modelling methods. Neuroinformatics (2019), 1--18.

[27]

John JM Reynolds, James S Plank, and Catherine D Schuman. 2019. Intelligent Reservoir Generation for Liquid State Machines using Evolutionary Optimization. In 2019 International Joint Conference on Neural Networks (IJCNN). IEEE, 1--8.

[28]

B. Schrauwen, D. Verstraeten, and J. Van Campenhout. 2007. An overview of reservoir computing: theory, applications and implementations. In Proceedings of the 15th european symposium on artificial neural networks. 471--482.

[29]

C.D. Schuman, G. Bruer, A.R. Young, M. Dean, and J.S. Plank. 2018. Understanding Selection And Diversity For Evolution Of Spiking Recurrent Neural Networks. In 2018 International Joint Conference on Neural Networks (IJCNN). IEEE, 1--8.

[30]

C.D. Schuman, A. Disney, S.P. Singh, G. Bruer, J.P. Mitchell, A. Klibisz, and J.S. Plank. 2016. Parallel evolutionary optimization for neuromorphic network training. In Proceedings of the Workshop on Machine Learning in High Performance Computing Environments. IEEE Press, 36--46.

Digital Library

[31]

C.D. Schuman, J.S. Plank, A. Disney, and J. Reynolds. 2016. An evolutionary optimization framework for neural networks and neuromorphic architectures. In 2016 International Joint Conference on Neural Networks (IJCNN). IEEE, 145--154.

[32]

C. D. Schuman, T. E. Potok, S. Young, R. Patton, G. Perdue, G. Chakma, A. Wyer, and G. S. Rose. 2017. Neuromorphic computing for temporal scientific data classification. In Neuromorphic Computing Symposium (NCS '17). ACM, New York, NY, USA, Article 2, 6 pages. https://doi.org/10.1145/3183584.3183612

Digital Library

[33]

William Severa, Craig M Vineyard, Ryan Dellana, Stephen J Verzi, and James B Aimone. 2019. Training deep neural networks for binary communication with the Whetstone method. Nature Machine Intelligence 1, 2 (2019), 86.

[34]

S.B. Shrestha and G. Orchard. 2018. SLAYER: Spike layer error reassignment in time. In Advances in Neural Information Processing Systems. 1412--1421.

[35]

K.O. Stanley and R. Miikkulainen. 2002. Evolving neural networks through augmenting topologies. Evolutionary computation 10, 2 (2002), 99--127.

[36]

Johannes C Thiele, Olivier Bichler, and Antoine Dupret. 2018. Event-based, timescale invariant unsupervised online deep learning with STDP. Frontiers in computational neuroscience 12 (2018), 46.

[37]

X. Yao. 1999. Evolving artificial neural networks. Proc. IEEE 87, 9 (1999), 1423--1447.

[38]

Steven R Young, Derek C Rose, Thomas P Karnowski, Seung-Hwan Lim, and Robert M Patton. 2015. Optimizing deep learning hyper-parameters through an evolutionary algorithm. In Proceedings of the Workshop on Machine Learning in High-Performance Computing Environments. ACM, 4.

Digital Library

Cited By

Wang ZGu XGoh RZhou JLuo T(2024)Efficient Spiking Neural Networks With Radix EncodingIEEE Transactions on Neural Networks and Learning Systems10.1109/TNNLS.2022.319591835:3(3689-3701)Online publication date: Mar-2024
https://doi.org/10.1109/TNNLS.2022.3195918
Kumar APark JZhou YKim JJain SSchuman CCauwenberghs GKuzum D(2024)Energy Efficient Implementation of MVM Operations Using Filament-Free Bulk RRAM Array2024 Neuro Inspired Computational Elements Conference (NICE)10.1109/NICE61972.2024.10549369(1-5)Online publication date: 23-Apr-2024
https://doi.org/10.1109/NICE61972.2024.10549369
Schuman CRizzo CRose GPlank J(2024)Embracing the Hairball: An Investigation of Recurrence in Spiking Neural Networks for Control2024 Neuro Inspired Computational Elements Conference (NICE)10.1109/NICE61972.2024.10548512(1-5)Online publication date: 23-Apr-2024
https://doi.org/10.1109/NICE61972.2024.10548512
Show More Cited By

Index Terms

Evolutionary Optimization for Neuromorphic Systems
1. Computing methodologies
  1. Machine learning
    1. Machine learning approaches
      1. Bio-inspired approaches
        Genetic algorithms
      2. Neural networks
2. Hardware
  1. Emerging technologies
    1. Biology-related information processing
      1. Neural systems

Recommendations

Algorithm and Application Impacts of Programmable Plasticity in Spiking Neuromorphic Hardware
ICONS '23: Proceedings of the 2023 International Conference on Neuromorphic Systems

Synaptic plasticity has long been thought to be key to learning in both biological neural networks and artificial neural networks. There are a wide array of plasticity rules in biological neural systems, but neuromorphic computing has mainly focused ...
Context-Dependent Computations in Spiking Neural Networks with Apical Modulation
Artificial Neural Networks and Machine Learning – ICANN 2023
Abstract
Neocortical pyramidal neurons integrate two distinct streams of information. Bottom-up information arrives at their basal dendrites, and resulting neuronal activity is modulated by top-down input that targets the apical tufts of these neurons and ...
Mapping spiking neural networks onto a manycore neuromorphic architecture
PLDI 2018: Proceedings of the 39th ACM SIGPLAN Conference on Programming Language Design and Implementation

We present a compiler for Loihi, a novel manycore neuromorphic processor that features a programmable, on-chip learning engine for training and executing spiking neural networks (SNNs). An SNN is distinguished from other neural networks in that (1) its ...

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences

NICE '20: Proceedings of the 2020 Annual Neuro-Inspired Computational Elements Workshop

March 2020

131 pages

ISBN:9781450377188

DOI:10.1145/3381755

Conference Chair:
Murat Okandan,
Program Chair:
James B. Aimone

Copyright © 2020 ACM.

Publication rights licensed to ACM. ACM acknowledges that this contribution was authored or co-authored by an employee, contractor or affiliate of the United States government. As such, the Government retains a nonexclusive, royalty-free right to publish or reproduce this article, or to allow others to do so, for Government purposes only.

In-Cooperation

INTEL: Intel Corporation
IBM: IBM

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 18 June 2020

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Conference

NICE '20

NICE '20: Neuro-inspired Computational Elements Workshop

March 17 - 20, 2020

Heidelberg, Germany

Acceptance Rates

Overall Acceptance Rate 25 of 40 submissions, 63%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

46
Total Citations
View Citations
507
Total Downloads

Downloads (Last 12 months)168
Downloads (Last 6 weeks)24

Reflects downloads up to 11 Aug 2024

Other Metrics

View Author Metrics

Citations

Cited By

Wang ZGu XGoh RZhou JLuo T(2024)Efficient Spiking Neural Networks With Radix EncodingIEEE Transactions on Neural Networks and Learning Systems10.1109/TNNLS.2022.319591835:3(3689-3701)Online publication date: Mar-2024
https://doi.org/10.1109/TNNLS.2022.3195918
Kumar APark JZhou YKim JJain SSchuman CCauwenberghs GKuzum D(2024)Energy Efficient Implementation of MVM Operations Using Filament-Free Bulk RRAM Array2024 Neuro Inspired Computational Elements Conference (NICE)10.1109/NICE61972.2024.10549369(1-5)Online publication date: 23-Apr-2024
https://doi.org/10.1109/NICE61972.2024.10549369
Schuman CRizzo CRose GPlank J(2024)Embracing the Hairball: An Investigation of Recurrence in Spiking Neural Networks for Control2024 Neuro Inspired Computational Elements Conference (NICE)10.1109/NICE61972.2024.10548512(1-5)Online publication date: 23-Apr-2024
https://doi.org/10.1109/NICE61972.2024.10548512
Das HSchuman CChakraborty NRose G(2024)Enhanced read resolution in reconfigurable memristive synapses for Spiking Neural NetworksScientific Reports10.1038/s41598-024-58947-214:1Online publication date: 17-Apr-2024
https://doi.org/10.1038/s41598-024-58947-2
Park JKumar AZhou YOh SKim JShi YJain SHota GQiu ENagle ASchuller ISchuman CCauwenberghs GKuzum D(2024)Multi-level, forming and filament free, bulk switching trilayer RRAM for neuromorphic computing at the edgeNature Communications10.1038/s41467-024-46682-115:1Online publication date: 25-Apr-2024
https://doi.org/10.1038/s41467-024-46682-1
Dey SDimitrov A(2023)Sensitivity analysis of point neuron model simulations implemented on neuromorphic hardwareFrontiers in Neuroscience10.3389/fnins.2023.119828217Online publication date: 24-Aug-2023
https://doi.org/10.3389/fnins.2023.1198282
Nilsson MSchelén OLindgren ABodin UPaniagua CDelsing JSandin F(2023)Integration of neuromorphic AI in event-driven distributed digitized systems: Concepts and research directionsFrontiers in Neuroscience10.3389/fnins.2023.107443917Online publication date: 17-Feb-2023
https://doi.org/10.3389/fnins.2023.1074439
Akl MErgene DWalter FKnoll A(2023)Toward robust and scalable deep spiking reinforcement learningFrontiers in Neurorobotics10.3389/fnbot.2022.107564716Online publication date: 20-Jan-2023
https://doi.org/10.3389/fnbot.2022.1075647
Vetter JDate PFahim FKulkarni SMaksymovych PTalin ATallada MVanna-iampikul PYoung ABrooks DCao YGu-Yeon WLim SLiu FMarinella MSumpter BMiniskar N(2023)Abisko: Deep codesign of an architecture for spiking neural networks using novel neuromorphic materialsThe International Journal of High Performance Computing Applications10.1177/1094342023117853737:3-4(351-379)Online publication date: 22-Jun-2023
https://doi.org/10.1177/10943420231178537
Snyder SZhu KVega RNowzari CParsa MPayvand MParsa MSchuman C(2023)Zespol: A Lightweight Environment for Training Swarming AgentsProceedings of the 2023 International Conference on Neuromorphic Systems10.1145/3589737.3606002(1-5)Online publication date: 1-Aug-2023
https://dl.acm.org/doi/10.1145/3589737.3606002
Show More Cited By

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents