Sparse ternary connect: Convolutional neural networks using ternarized weights with enhanced sparsity

研究成果: Conference contribution

3 被引用数 (Scopus)

抄録

Convolutional Neural Networks (CNNs) are indispensable in a wide range of tasks to achieve state-of-the-art results. In this work, we exploit ternary weights in both inference and training of CNNs and further propose Sparse Ternary Connect (STC) where kernel weights in float value are converted to 1, -1 and 0 based on a new conversion rule with the controlled ratio of 0. STC can save hardware resource a lot with small degradation of precision. The experimental evaluation on 2 popular datasets (CIFAR-10 and SVHN) shows that the proposed method can reduce resource utilization (by 28.9% of LUT, 25.3% of FF, 97.5% of DSP and 88.7% of BRAM on Xilinx Kintex-7 FPGA) with less than 0.5% accuracy loss.

本文言語English
ホスト出版物のタイトルASP-DAC 2018 - 23rd Asia and South Pacific Design Automation Conference, Proceedings
出版社Institute of Electrical and Electronics Engineers Inc.
ページ190-195
ページ数6
ISBN(電子版)9781509006021
DOI
出版ステータスPublished - 2018 2 20
イベント23rd Asia and South Pacific Design Automation Conference, ASP-DAC 2018 - Jeju, Korea, Republic of
継続期間: 2018 1 222018 1 25

出版物シリーズ

名前Proceedings of the Asia and South Pacific Design Automation Conference, ASP-DAC
2018-January

Other

Other23rd Asia and South Pacific Design Automation Conference, ASP-DAC 2018
国/地域Korea, Republic of
CityJeju
Period18/1/2218/1/25

ASJC Scopus subject areas

  • 電子工学および電気工学
  • コンピュータ サイエンスの応用
  • コンピュータ グラフィックスおよびコンピュータ支援設計

フィンガープリント

「Sparse ternary connect: Convolutional neural networks using ternarized weights with enhanced sparsity」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