{"title":"一种新的双相神经元编码器实现","authors":"Madhuvanthi Srivatsav R, B. Kailath","doi":"10.1109/AIIoT52608.2021.9454233","DOIUrl":null,"url":null,"abstract":"In an effort to address the issue of low power and area constraints which are important pre-requisites to many applications in the field of signal processing, this work focuses on the implementation of a novel biphasic neuron architecture, that is proven to be energy efficient, and highly compact. The low power Adaptive exponential integrate and fire neuron (ADEx I&F), is implemented as a biphasic encoder in 180 nm CMOS Technology, and a SER of upto 60 dB and a figure of merit (FOM) of 0.26 pJ/conversion is achieved. The proposed biphasic encoder is found to exhibit similar performance characteristics with respect to the existing architectures while comprising of 52 % lesser number of transistors than the conventional biphasic neuron encoder models.","PeriodicalId":443405,"journal":{"name":"2021 IEEE World AI IoT Congress (AIIoT)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A Novel Biphasic Neuron Encoder Implementation\",\"authors\":\"Madhuvanthi Srivatsav R, B. Kailath\",\"doi\":\"10.1109/AIIoT52608.2021.9454233\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In an effort to address the issue of low power and area constraints which are important pre-requisites to many applications in the field of signal processing, this work focuses on the implementation of a novel biphasic neuron architecture, that is proven to be energy efficient, and highly compact. The low power Adaptive exponential integrate and fire neuron (ADEx I&F), is implemented as a biphasic encoder in 180 nm CMOS Technology, and a SER of upto 60 dB and a figure of merit (FOM) of 0.26 pJ/conversion is achieved. The proposed biphasic encoder is found to exhibit similar performance characteristics with respect to the existing architectures while comprising of 52 % lesser number of transistors than the conventional biphasic neuron encoder models.\",\"PeriodicalId\":443405,\"journal\":{\"name\":\"2021 IEEE World AI IoT Congress (AIIoT)\",\"volume\":\"34 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-05-10\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2021 IEEE World AI IoT Congress (AIIoT)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/AIIoT52608.2021.9454233\",\"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 IEEE World AI IoT Congress (AIIoT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/AIIoT52608.2021.9454233","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
In an effort to address the issue of low power and area constraints which are important pre-requisites to many applications in the field of signal processing, this work focuses on the implementation of a novel biphasic neuron architecture, that is proven to be energy efficient, and highly compact. The low power Adaptive exponential integrate and fire neuron (ADEx I&F), is implemented as a biphasic encoder in 180 nm CMOS Technology, and a SER of upto 60 dB and a figure of merit (FOM) of 0.26 pJ/conversion is achieved. The proposed biphasic encoder is found to exhibit similar performance characteristics with respect to the existing architectures while comprising of 52 % lesser number of transistors than the conventional biphasic neuron encoder models.