A Zero-Gating Processing Element Design for Low-Power Deep Convolutional Neural Networks

研究成果

1 被引用数 (Scopus)

抄録

Convolution neural networks (CNNs) have shown great success in many areas such as object detection and pattern recognition. However, the high computational complexity of state-of-the-art deep CNNs makes them extreme difficult to be run on resource-constrained mobile and wearable devices. To address this design challenge, in this paper we first analyzed the filters' weights of pre-trained models from four state-of-the-art CNNs. We found that in all the CNNs that we analyzed, from about 20% (AlexNet) to 43% (VGG-19) of the weights are zeros, which lead to redundant large amounts of computation. Then, based on this observation, a zero-gating processing element (PE) design was proposed for low-power deep CNNs, in which the vast number of zeros in both activation maps and filter weights are explored to eliminate redundant computation for power reduction. We implemented our proposal with VGG-16 using ImageNet dataset. Experiments were conducted for evaluations of area and total power consumption. Compared with the baseline PE design without zero-gating, overall the proposed zero-gating PE can achieve 37% power saving while the corresponding area overhead is less than 8%.

本文言語English
ホスト出版物のタイトルProceedings - APCCAS 2019
ホスト出版物のサブタイトル2019 IEEE Asia Pacific Conference on Circuits and Systems: Innovative CAS Towards Sustainable Energy and Technology Disruption
出版社Institute of Electrical and Electronics Engineers Inc.
ページ317-320
ページ数4
ISBN(電子版)9781728129402
DOI
出版ステータスPublished - 2019 11
イベント15th Annual IEEE Asia Pacific Conference on Circuits and Systems, APCCAS 2019 - Bangkok, Thailand
継続期間: 2019 11 112019 11 14

出版物シリーズ

名前Proceedings - APCCAS 2019: 2019 IEEE Asia Pacific Conference on Circuits and Systems: Innovative CAS Towards Sustainable Energy and Technology Disruption

Conference

Conference15th Annual IEEE Asia Pacific Conference on Circuits and Systems, APCCAS 2019
国/地域Thailand
CityBangkok
Period19/11/1119/11/14

ASJC Scopus subject areas

  • エネルギー工学および電力技術
  • 再生可能エネルギー、持続可能性、環境
  • 電子工学および電気工学
  • 電子材料、光学材料、および磁性材料
  • 器械工学

フィンガープリント

「A Zero-Gating Processing Element Design for Low-Power Deep Convolutional Neural Networks」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル