Daniel Albrecht and Catherine Schuman

July, 2020

ICONS: International Conference on Neuromorphic Systems

https://dl.acm.org/doi/proceedings/10.1145/3407197

View Article

Abstract

Spiking neural networks (SNNs) offer tremendous potential for the future of AI, including the ability to be implemented efficiently on neuromorphic systems. One of the challenges in building functioning SNNs is the training process, as standard error back-propagation cannot be easily applied. In this work, we extend an evolutionary approach for training SNNs by implementing an indirect encoding of individuals. Specifically, we evolve SNNs using Compositional Pattern Producing Networks, which are able to learn the connectivity patterns between neurons defined in a coordinate space. We validate the approach on multiple control and classification tasks.

Citation Information

Text

author     D. Elbrecht and C. Schuman
title      Neuroevolution of Spiking Neural Networks Using Compositional 
           Pattern Producing Networks
booktitle  International Conference on Neuromorphic Computing Systems (ICONS)
publisher  ACM
month      July
year       2020
doi        10.1145/3407197.3407198
url        https://dl.acm.org/doi/10.1145/3407197.3407198

Bibtex

@INPROCEEDINGS{es:20:nsn,
    author = "D. Elbrecht and C. Schuman",
    title = "Neuroevolution of Spiking Neural Networks Using Compositional 
               Pattern Producing Networks",
    booktitle = "International Conference on Neuromorphic Computing Systems (ICONS)",
    publisher = "ACM",
    month = "July",
    year = "2020",
    doi = "10.1145/3407197.3407198",
    url = "https://dl.acm.org/doi/10.1145/3407197.3407198"
}