- 【Updated on May 12, 2025】 Integration of CiNii Dissertations and CiNii Books into CiNii Research
- Trial version of CiNii Research Knowledge Graph Search feature is available on CiNii Labs
- 【Updated on June 30, 2025】Suspension and deletion of data provided by Nikkei BP
- Regarding the recording of “Research Data” and “Evidence Data”
Construction and Input-to-output Characteristics Evaluation of Compressed Model of Recurrent Neural Networks for Their Stability Analysis
-
- 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
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
-
- Transactions of the Society of Instrument and Control Engineers
-
Transactions of the Society of Instrument and Control Engineers 61 (3), 104-114, 2025
The Society of Instrument and Control Engineers