Archita Hore, S. Panda, Ayan Chakraborty, Sharba Bandyopadhyay, S. Chakrabarti
{"title":"基于亚阈值方法的CMOS神经元设计中脉冲宽度对脉冲频率的影响","authors":"Archita Hore, S. Panda, Ayan Chakraborty, Sharba Bandyopadhyay, S. Chakrabarti","doi":"10.1109/ACTS53447.2021.9708326","DOIUrl":null,"url":null,"abstract":"Neuromorphic circuits employ analog, digital or mixed signal operations to mimic the electrophysiological behaviour of a brain. A CMOS neuron circuit has been designed. This neuronal circuit has the capability to control several features of a neuron including spike width. A unique aspect of this study is that when spike width is decreased, spiking frequency of the circuit increases similar to biological neurons. The effects of spike width variation on other features such as mean inter spike interval and spike height have also been discussed. Further, the effects of temperature on the width of an action potential have been demonstrated. Performance of the circuit in terms of average power dissipation and energy consumption per spike have been evaluated. The proposed circuit looks promising to incorporate bio-plausible diversity in next generation spiking neural network architectures.","PeriodicalId":201741,"journal":{"name":"2021 Advanced Communication Technologies and Signal Processing (ACTS)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Effects of Spike Width on Spiking Frequency in a CMOS Neuron Design Following a Subthreshold Approach\",\"authors\":\"Archita Hore, S. Panda, Ayan Chakraborty, Sharba Bandyopadhyay, S. Chakrabarti\",\"doi\":\"10.1109/ACTS53447.2021.9708326\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Neuromorphic circuits employ analog, digital or mixed signal operations to mimic the electrophysiological behaviour of a brain. A CMOS neuron circuit has been designed. This neuronal circuit has the capability to control several features of a neuron including spike width. A unique aspect of this study is that when spike width is decreased, spiking frequency of the circuit increases similar to biological neurons. The effects of spike width variation on other features such as mean inter spike interval and spike height have also been discussed. Further, the effects of temperature on the width of an action potential have been demonstrated. Performance of the circuit in terms of average power dissipation and energy consumption per spike have been evaluated. The proposed circuit looks promising to incorporate bio-plausible diversity in next generation spiking neural network architectures.\",\"PeriodicalId\":201741,\"journal\":{\"name\":\"2021 Advanced Communication Technologies and Signal Processing (ACTS)\",\"volume\":\"11 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-12-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2021 Advanced Communication Technologies and Signal Processing (ACTS)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ACTS53447.2021.9708326\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 Advanced Communication Technologies and Signal Processing (ACTS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ACTS53447.2021.9708326","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Effects of Spike Width on Spiking Frequency in a CMOS Neuron Design Following a Subthreshold Approach
Neuromorphic circuits employ analog, digital or mixed signal operations to mimic the electrophysiological behaviour of a brain. A CMOS neuron circuit has been designed. This neuronal circuit has the capability to control several features of a neuron including spike width. A unique aspect of this study is that when spike width is decreased, spiking frequency of the circuit increases similar to biological neurons. The effects of spike width variation on other features such as mean inter spike interval and spike height have also been discussed. Further, the effects of temperature on the width of an action potential have been demonstrated. Performance of the circuit in terms of average power dissipation and energy consumption per spike have been evaluated. The proposed circuit looks promising to incorporate bio-plausible diversity in next generation spiking neural network architectures.