Construction and Input-to-output Characteristics Evaluation of Compressed Model of Recurrent Neural Networks for Their Stability Analysis

DOI Web Site Web Site 9 References
  • YUNO Tsuyoshi
    Faculty/Graduate School of Information Science and Electrical Engineering, Kyushu University
  • FUKUCHI Kazuma
    Faculty/Graduate School of Information Science and Electrical Engineering, Kyushu University
  • EBIHARA Yoshio
    Faculty/Graduate School of Information Science and Electrical Engineering, Kyushu University

Bibliographic Information

Other Title
  • 再帰型ニューラルネットワークの安定性判別のための圧縮モデルの構築と入出力特性の評価
  • サイキガタ ニューラルネットワーク ノ アンテイセイ ハンベツ ノ タメ ノ アッシュク モデル ノ コウチク ト ニュウシュツリョク トクセイ ノ ヒョウカ
Published
2025
Resource Type
journal article
DOI
  • 10.9746/sicetr.61.104
Publisher
The Society of Instrument and Control Engineers

Search this article

Description

<p>This paper proposes a model compression method of reducing the number of nonlinear activation functions of continuous-time recurrent neural networks (RNNs). Ensuring the internal stability of the compressed RNN guarantees that of the original RNN. An error bound between the outputs of the compressed RNN and the original one is derived. Moreover, an optimization problem for reducing the bound is formulated, and it is relaxed to a semi-definite programming problem. Furthermore, it is shown that the proposed model compression method produces a compressed RNN whose output is close to that of the original one as a general tendency. The proposed method is demonstrated on a simple numerical example.</p>

Journal

References(9)*help

See more

Related Projects

See more

Keywords

Details 詳細情報について

Report a problem

Back to top