Evolving Spiking Circuit Motifs Using Weight Agnostic Neural Networks

Abstract

Neural architecture search (NAS) has emerged as an algorithmic method of developing neural network architectures. Weight Agnostic Neural Networks (WANNs) are an evolutionary-based NAS approach. Fundamentally, WANNs find network structures that are relatively insensitive to shifts in weight values and are typically much smaller than an equivalent performance dense network. Here, we extend the WANN framework to search for spiking circuits and in doing so investigate whether these circuit motifs can also yield task performance that is weight agnostic. We analyze properties such as the complexity of the solution, as well as performance. Our results successfully show the performance of spiking WANNs on several exemplar tasks.

Cite

Text

Anwar. "Evolving Spiking Circuit Motifs Using Weight Agnostic Neural Networks." AAAI Conference on Artificial Intelligence, 2021. doi:10.1609/AAAI.V35I18.17974

Markdown

[Anwar. "Evolving Spiking Circuit Motifs Using Weight Agnostic Neural Networks." AAAI Conference on Artificial Intelligence, 2021.](https://mlanthology.org/aaai/2021/anwar2021aaai-evolving/) doi:10.1609/AAAI.V35I18.17974

BibTeX

@inproceedings{anwar2021aaai-evolving,
  title     = {{Evolving Spiking Circuit Motifs Using Weight Agnostic Neural Networks}},
  author    = {Anwar, Abrar},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2021},
  pages     = {15956-15957},
  doi       = {10.1609/AAAI.V35I18.17974},
  url       = {https://mlanthology.org/aaai/2021/anwar2021aaai-evolving/}
}