Full text

Turn on search term navigation

© 2024. This work is published under https://creativecommons.org/licenses/by/4.0/ (the "License"). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.

Abstract

Spiking neural networks (SNNs) have emerged as a novel approach for reducing computational costs by mimicking the biologically plausible operations of neurons and synapses. In this article, large‐scale analog SNNs are investigated and optimized at the hardware‐level by using SNNSim, the novel simulator for SNNs that employ analog synaptic devices and integrate‐and‐fire (I&F) neuron circuits. SNNSim is a reconfigurable simulator that accurately and very quickly models the behavior of the user‐defined device characteristics and returns key metrics such as area, accuracy, latency, and power consumption as output. Notably, SNNSim exhibits exceptional efficiency, as it can process the entire 10 000 Modified National Institute of Standards and Technology (MNIST) test dataset in a few seconds, whereas SPICE simulations require hours to simulate a single MNIST test data. Using SNNSim, the conversion of artificial neural networks (ANNs) to SNNs is simulated and the performance of the large‐scale analog SNNs is optimized. The results enable the design of accurate, high‐speed, and low‐power operation of large‐scale SNNs. SNNSim code is now available at https://github.com/SMDLGITHUB/SNNSim.

Details

Title
SNNSim: Investigation and Optimization of Large‐Scale Analog Spiking Neural Networks Based on Flash Memory Devices
Author
Ko, Jonghyun 1 ; Kwon, Dongseok 1 ; Hwang, Joon 1 ; Lee, Kyu‐Ho 1 ; Oh, Seongbin 1 ; Kim, Jeonghyun 1 ; Im, Jiseong 1 ; Koo, Ryun‐Han 1 ; Kim, Jae‐Joon 1 ; Lee, Jong‐Ho 1   VIAFID ORCID Logo 

 Department of Electrical and Computer Engineering and Inter‐university Semiconductor Research Center, Seoul National University, Gwanak‐gu, Seoul, South Korea 
Section
Research Articles
Publication year
2024
Publication date
Apr 1, 2024
Publisher
John Wiley & Sons, Inc.
e-ISSN
26404567
Source type
Scholarly Journal
Language of publication
English
ProQuest document ID
3143066351
Copyright
© 2024. This work is published under https://creativecommons.org/licenses/by/4.0/ (the "License"). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.