Deep Neural Network Pruning Using Persistent Homology

Satoru Watanabe, Hayato Yamana

研究成果: Conference contribution

抄録

Deep neural networks (DNNs) have improved the performance of artificial intelligence systems in various fields including image analysis, speech recognition, and text classification. However, the consumption of enormous computation resources prevents DNNs from operating on small computers such as edge sensors and handheld devices. Network pruning (NP), which removes parameters from trained DNNs, is one of the prominent methods of reducing the resource consumption of DNNs. In this paper, we propose a novel method of NP, hereafter referred to as PHPM, using persistent homology (PH). PH investigates the inner representation of knowledge in DNNs, and PHPM utilizes the investigation in NP to improve the efficiency of pruning. PHPM prunes DNNs in ascending order of magnitudes of the combinational effects among neurons, which are calculated using the one-dimensional PH, to prevent the deterioration of the accuracy. We compared PHPM with global magnitude pruning method (GMP), which is one of the common baselines to evaluate pruning methods. Evaluation results show that the classification accuracy of DNNs pruned by PHPM outperforms that pruned by GMP.

本文言語English
ホスト出版物のタイトルProceedings - 2020 IEEE 3rd International Conference on Artificial Intelligence and Knowledge Engineering, AIKE 2020
出版社Institute of Electrical and Electronics Engineers Inc.
ページ153-156
ページ数4
ISBN(電子版)9781728187082
DOI
出版ステータスPublished - 2020 12
イベント3rd IEEE International Conference on Artificial Intelligence and Knowledge Engineering, AIKE 2020 - Irvine, United States
継続期間: 2020 12 92020 12 11

出版物シリーズ

名前Proceedings - 2020 IEEE 3rd International Conference on Artificial Intelligence and Knowledge Engineering, AIKE 2020

Conference

Conference3rd IEEE International Conference on Artificial Intelligence and Knowledge Engineering, AIKE 2020
国/地域United States
CityIrvine
Period20/12/920/12/11

ASJC Scopus subject areas

  • 人工知能
  • コンピュータ ネットワークおよび通信
  • ハードウェアとアーキテクチャ
  • 信号処理
  • 情報システムおよび情報管理

フィンガープリント

「Deep Neural Network Pruning Using Persistent Homology」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