Presentation 2011-07-25
Stability Analysis on Multistate Hopfield Neural Networks Based on Commutative Quaternion
Teijiro ISOKAWA, Haruhiko NISHIMURA, Nobuyuki MATSUI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Two types of multistate Hopfield neural networks are explored in this paper. These networks are based on commutative quaternions that are similar to Hamilton's quaternions but with commutative multiplication. In one type of the networks, the state of a neuron is represented by two kinds of phases and one real number. The other type of the networks adopts the decomposed form of commutative quaternion. In this network, the state of a neuron consists of a combination of two complex values. The stabilities of these networks are proven, i.e., the energies never increase with respect to the state changes.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Commutative Quaternion / Quaternion / Hopfield Neural Network / Idempotent base / Complex-valued Neural Network
Paper # NC2011-20
Date of Issue

Conference Information
Committee NC
Conference Date 2011/7/18(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 Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Stability Analysis on Multistate Hopfield Neural Networks Based on Commutative Quaternion
Sub Title (in English)
Keyword(1) Commutative Quaternion
Keyword(2) Quaternion
Keyword(3) Hopfield Neural Network
Keyword(4) Idempotent base
Keyword(5) Complex-valued Neural Network
1st Author's Name Teijiro ISOKAWA
1st Author's Affiliation Graduate School of Engineering, University of Hyogo()
2nd Author's Name Haruhiko NISHIMURA
2nd Author's Affiliation Graduate School of Applied Informatics, University of Hyogo
3rd Author's Name Nobuyuki MATSUI
3rd Author's Affiliation Graduate School of Engineering, University of Hyogo
Date 2011-07-25
Paper # NC2011-20
Volume (vol) vol.111
Number (no) 157
Page pp.pp.-
#Pages 6
Date of Issue