Brief Report
Version 1
This version is not peer-reviewed
Noise as an Optimization Tool for Spiking Neural Networks
Version 1
: Received: 9 August 2024 / Approved: 9 August 2024 / Online: 9 August 2024 (10:28:12 CEST)
How to cite: Garipova, Y.; Yonekura, S.; Kuniyoshi, Y. Noise as an Optimization Tool for Spiking Neural Networks. Preprints 2024, 2024080704. https://doi.org/10.20944/preprints202408.0704.v1 Garipova, Y.; Yonekura, S.; Kuniyoshi, Y. Noise as an Optimization Tool for Spiking Neural Networks. Preprints 2024, 2024080704. https://doi.org/10.20944/preprints202408.0704.v1
Abstract
Standard ANNs lack flexibility when handling corrupted input due to their fixed structure. Spiking Neural Networks (SNNs) can utilize biological temporal coding features, such as noise-induced stochastic resonance and dynamical synapses to increase a model’s performance when its parameters are not optimized for a given input. Using the analog XOR task as a simplified Convolutional Neural Network analog, this paper demonstrates two key results: (1) SNNs solve the problem linearly inseparable in ANN with over 10% improvement in the optimal setting, and (2) in SNNs, the synaptic noise and dynamical synapses compensate for non-optimal parameters, achieving near-optimal results.
Keywords
spiking neural networks; adaptability; noise
Subject
Computer Science and Mathematics, Artificial Intelligence and Machine Learning
Copyright: This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Comments (0)
We encourage comments and feedback from a broad range of readers. See criteria for comments and our Diversity statement.
Leave a public commentSend a private comment to the author(s)
* All users must log in before leaving a comment