TY - GEN
T1 - Evolving Ensembles of Spiking Neural Networks for Neuromorphic Systems
AU - Elbrecht, Daniel
AU - Kulkarni, Shruti R.
AU - Parsa, Maryam
AU - Mitchell, J. Parker
AU - Schuman, Catherine D.
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/12/1
Y1 - 2020/12/1
N2 - Evolutionary algorithms have been proposed as a solution to overcome many of the challenges associated with training spiking neural networks. While evolutionary optimization for spiking neural networks is very flexible, its performance has difficulty scaling to complex tasks and correspondingly complex network structures. Here we propose a method for evolving ensembles of spiking neural networks. By using ensemble learning, the flexibility of evolutionary optimization is fully preserved while scaling to more challenging tasks. We test the performance of the proposed method using handwritten digit classification. We investigate multiple strategies for constructing ensembles of spiking neural networks, and demonstrate that evolving ensembles of SNNs offers significant performance advantages over evolutionary optimization.
AB - Evolutionary algorithms have been proposed as a solution to overcome many of the challenges associated with training spiking neural networks. While evolutionary optimization for spiking neural networks is very flexible, its performance has difficulty scaling to complex tasks and correspondingly complex network structures. Here we propose a method for evolving ensembles of spiking neural networks. By using ensemble learning, the flexibility of evolutionary optimization is fully preserved while scaling to more challenging tasks. We test the performance of the proposed method using handwritten digit classification. We investigate multiple strategies for constructing ensembles of spiking neural networks, and demonstrate that evolving ensembles of SNNs offers significant performance advantages over evolutionary optimization.
KW - ensembles
KW - evolutionary algorithms
KW - neuromorphic computing
KW - spiking neural networks
UR - http://www.scopus.com/inward/record.url?scp=85099718621&partnerID=8YFLogxK
U2 - 10.1109/SSCI47803.2020.9308568
DO - 10.1109/SSCI47803.2020.9308568
M3 - Conference contribution
AN - SCOPUS:85099718621
T3 - 2020 IEEE Symposium Series on Computational Intelligence, SSCI 2020
SP - 1989
EP - 1994
BT - 2020 IEEE Symposium Series on Computational Intelligence, SSCI 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2020 IEEE Symposium Series on Computational Intelligence, SSCI 2020
Y2 - 1 December 2020 through 4 December 2020
ER -