Neuroevolution Guided Hybrid Spiking Neural Network Training

Research output: Contribution to journalArticlepeer-review

2 Scopus citations

Abstract

Neuromorphic computing algorithms based on Spiking Neural Networks (SNNs) are evolving to be a disruptive technology driving machine learning research. The overarching goal of this work is to develop a structured algorithmic framework for SNN training that optimizes unique SNN-specific properties like neuron spiking threshold using neuroevolution as a feedback strategy. We provide extensive results for this hybrid bio-inspired training strategy and show that such a feedback-based learning approach leads to explainable neuromorphic systems that adapt to the specific underlying application. Our analysis reveals 53.8, 28.8, and 28.2% latency improvement for the neuroevolution-based SNN training strategy on CIFAR-10, CIFAR-100, and ImageNet datasets, respectively in contrast to state-of-the-art conversion based approaches. The proposed algorithm can be easily extended to other application domains like image classification in presence of adversarial attacks where 43.2 and 27.9% latency improvements were observed on CIFAR-10 and CIFAR-100 datasets, respectively.

Original languageEnglish (US)
Article number838523
JournalFrontiers in Neuroscience
Volume16
DOIs
StatePublished - Apr 25 2022

All Science Journal Classification (ASJC) codes

  • Neuroscience(all)

Fingerprint

Dive into the research topics of 'Neuroevolution Guided Hybrid Spiking Neural Network Training'. Together they form a unique fingerprint.

Cite this