数字神经形态硬件的深度尖峰二值神经网络

2020 IEEE 15th International Conference on Solid-State & Integrated Circuit Technology (ICSICT) Pub Date : 2020-11-03 DOI:10.1109/ICSICT49897.2020.9278275

Zilin Wang, Kefei Liu, Xiaoxin Cui, Yuan Wang

{"title":"数字神经形态硬件的深度尖峰二值神经网络","authors":"Zilin Wang, Kefei Liu, Xiaoxin Cui, Yuan Wang","doi":"10.1109/ICSICT49897.2020.9278275","DOIUrl":null,"url":null,"abstract":"The spiking neural network (SNN) converted from artificial neural network (ANN) usually contains many high-precision parameters. This will cause a lot of hardware resources to be consumed. A spiking binary neural network is proposed in this paper, whose weights are binary and it does not contain high-precision parameters. Experimental results show that the proposed network can be adapted to the neuromorphic chip and reduce memory consumption by 16 times without much loss of accuracy.","PeriodicalId":6727,"journal":{"name":"2020 IEEE 15th International Conference on Solid-State & Integrated Circuit Technology (ICSICT)","volume":"22 1","pages":"1-3"},"PeriodicalIF":0.0000,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Deep Spiking Binary Neural Network for Digital Neuromorphic Hardware\",\"authors\":\"Zilin Wang, Kefei Liu, Xiaoxin Cui, Yuan Wang\",\"doi\":\"10.1109/ICSICT49897.2020.9278275\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The spiking neural network (SNN) converted from artificial neural network (ANN) usually contains many high-precision parameters. This will cause a lot of hardware resources to be consumed. A spiking binary neural network is proposed in this paper, whose weights are binary and it does not contain high-precision parameters. Experimental results show that the proposed network can be adapted to the neuromorphic chip and reduce memory consumption by 16 times without much loss of accuracy.\",\"PeriodicalId\":6727,\"journal\":{\"name\":\"2020 IEEE 15th International Conference on Solid-State & Integrated Circuit Technology (ICSICT)\",\"volume\":\"22 1\",\"pages\":\"1-3\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-11-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 IEEE 15th International Conference on Solid-State & Integrated Circuit Technology (ICSICT)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICSICT49897.2020.9278275\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 IEEE 15th International Conference on Solid-State & Integrated Circuit Technology (ICSICT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICSICT49897.2020.9278275","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 2

摘要

由人工神经网络(ANN)转化而来的峰值神经网络(SNN)通常包含许多高精度参数。这将导致大量硬件资源被消耗。提出了一种权值为二值且不含高精度参数的尖峰二值神经网络。实验结果表明，该网络可以适应神经形态芯片，在不降低准确率的情况下，将内存消耗降低了16倍。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Deep Spiking Binary Neural Network for Digital Neuromorphic Hardware

The spiking neural network (SNN) converted from artificial neural network (ANN) usually contains many high-precision parameters. This will cause a lot of hardware resources to be consumed. A spiking binary neural network is proposed in this paper, whose weights are binary and it does not contain high-precision parameters. Experimental results show that the proposed network can be adapted to the neuromorphic chip and reduce memory consumption by 16 times without much loss of accuracy.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

2020 IEEE 15th International Conference on Solid-State & Integrated Circuit Technology (ICSICT)

自引率

0.00%

发文量