Presentation 1995/5/19
Construction of Digital Filter from a Recurrent Neural Network
Ken-ichi Okuno, Naoki Isu, Hiroki Yoshimura, Tadaaki Shimizu, Kazuhiro Sugata,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Digital filters were constructed from fully cross-coupled and partially cross-coupled recurrent neural networks by the use of the back propagation through time (BPTT) learning. Maximum length linear shift register sequence (M sequence) was adopted as an input signal to the networks, and its expected output from a filter to be constructed was given as a teacher signal. Partially cross-coupled recurrent neural networks modeled after Direct Types I and II of IIR digital filter acquired appropriate properties of LPF and HPF through learning. It was also shown that a recurrent neural network has the ability to construct any filters with complex dynamics by the same learning process.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Recurrent Neural Network / Digital Filter / BPTT / M Sequence
Paper #
Date of Issue

Conference Information
Committee NLP
Conference Date 1995/5/19(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Nonlinear Problems (NLP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Construction of Digital Filter from a Recurrent Neural Network
Sub Title (in English)
Keyword(1) Recurrent Neural Network
Keyword(2) Digital Filter
Keyword(3) BPTT
Keyword(4) M Sequence
1st Author's Name Ken-ichi Okuno
1st Author's Affiliation Dept. of Information and Knowledge Engineering Faculty of Engineering, Tottori University()
2nd Author's Name Naoki Isu
2nd Author's Affiliation Dept. of Information and Knowledge Engineering Faculty of Engineering, Tottori University
3rd Author's Name Hiroki Yoshimura
3rd Author's Affiliation Dept. of Information and Knowledge Engineering Faculty of Engineering, Tottori University
4th Author's Name Tadaaki Shimizu
4th Author's Affiliation Dept. of Information and Knowledge Engineering Faculty of Engineering, Tottori University
5th Author's Name Kazuhiro Sugata
5th Author's Affiliation Dept. of Information and Knowledge Engineering Faculty of Engineering, Tottori University
Date 1995/5/19
Paper #
Volume (vol) vol.95
Number (no) 47
Page pp.pp.-
#Pages 8
Date of Issue