Structure discovery of deep neural network based on evolutionary algorithms

Takahiro Shinozaki, Shinji Watanabe

研究成果: Conference contribution

23 引用 (Scopus)

抜粋

Deep neural networks (DNNs) are constructed by considering highly complicated configurations including network structure and several tuning parameters (number of hidden states and learning rate in each layer), which greatly affect the performance of speech processing applications. To reach optimal performance in such systems, deep understanding and expertise in DNNs is necessary, which limits the development of DNN systems to skilled experts. To overcome the problem, this paper proposes an efficient optimization strategy for DNN structure and parameters using evolutionary algorithms. The proposed approach parametrizes the DNN structure by a directed acyclic graph, and the DNN structure is represented by a simple binary vector. Genetic algorithm and covariance matrix adaptation evolution strategy efficiently optimize the performance jointly with respect to the above binary vector and the other tuning parameters. Experiments on phoneme recognition and spoken digit detection tasks show the effectiveness of the proposed approach by discovering the appropriate DNN structure automatically.

元の言語English
ホスト出版物のタイトル2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings
出版者Institute of Electrical and Electronics Engineers Inc.
ページ4979-4983
ページ数5
ISBN(電子版)9781467369978
DOI
出版物ステータスPublished - 2015 8 4
外部発表Yes
イベント40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Brisbane, Australia
継続期間: 2014 4 192014 4 24

出版物シリーズ

名前ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
2015-August
ISSN(印刷物)1520-6149

Other

Other40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015
Australia
Brisbane
期間14/4/1914/4/24

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

フィンガープリント Structure discovery of deep neural network based on evolutionary algorithms' の研究トピックを掘り下げます。これらはともに一意のフィンガープリントを構成します。

  • これを引用

    Shinozaki, T., & Watanabe, S. (2015). Structure discovery of deep neural network based on evolutionary algorithms. : 2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings (pp. 4979-4983). [7178918] (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; 巻数 2015-August). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2015.7178918