{"title":"基于多模加速器的深度神经网络","authors":"A. Ardakani, C. Condo, W. Gross","doi":"10.1109/NEWCAS.2018.8585517","DOIUrl":null,"url":null,"abstract":"Convolutional Neural Networks (CNNs) are constituted of complex, slow convolutional layers and memory-demanding fully- connected layers. Current pruning techniques can reduce memory accesses and power consumption, but cannot speed up the convolutional layers. In this paper, we introduce a pruning technique able to reduce the number of kernels in convolutional layers of up to 90% with negligible accuracy degradation. We propose an architecture to accelerate fully- connected and convolutional computations within a single computational core, with power$/$energy consumption below mobile devices budget. The proposed pruning technique speeds up convolutional computations by up to $ 6.9\\times $, reducing memory accesses by the same factor.","PeriodicalId":112526,"journal":{"name":"2018 16th IEEE International New Circuits and Systems Conference (NEWCAS)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A Multi-Mode Accelerator for Pruned Deep Neural Networks\",\"authors\":\"A. Ardakani, C. Condo, W. Gross\",\"doi\":\"10.1109/NEWCAS.2018.8585517\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Convolutional Neural Networks (CNNs) are constituted of complex, slow convolutional layers and memory-demanding fully- connected layers. Current pruning techniques can reduce memory accesses and power consumption, but cannot speed up the convolutional layers. In this paper, we introduce a pruning technique able to reduce the number of kernels in convolutional layers of up to 90% with negligible accuracy degradation. We propose an architecture to accelerate fully- connected and convolutional computations within a single computational core, with power$/$energy consumption below mobile devices budget. The proposed pruning technique speeds up convolutional computations by up to $ 6.9\\\\times $, reducing memory accesses by the same factor.\",\"PeriodicalId\":112526,\"journal\":{\"name\":\"2018 16th IEEE International New Circuits and Systems Conference (NEWCAS)\",\"volume\":\"38 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2018-06-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2018 16th IEEE International New Circuits and Systems Conference (NEWCAS)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/NEWCAS.2018.8585517\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 16th IEEE International New Circuits and Systems Conference (NEWCAS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/NEWCAS.2018.8585517","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
A Multi-Mode Accelerator for Pruned Deep Neural Networks
Convolutional Neural Networks (CNNs) are constituted of complex, slow convolutional layers and memory-demanding fully- connected layers. Current pruning techniques can reduce memory accesses and power consumption, but cannot speed up the convolutional layers. In this paper, we introduce a pruning technique able to reduce the number of kernels in convolutional layers of up to 90% with negligible accuracy degradation. We propose an architecture to accelerate fully- connected and convolutional computations within a single computational core, with power$/$energy consumption below mobile devices budget. The proposed pruning technique speeds up convolutional computations by up to $ 6.9\times $, reducing memory accesses by the same factor.