Temporal sequences of patterns with an inverse function delayed Neural network

Johan Sveholm; Yoshihiro Hayakawa; Koji Nakajima

doi:10.1093/ietfec/e89-a.10.2818

Temporal sequences of patterns with an inverse function delayed Neural network

Johan Sveholm, Yoshihiro Hayakawa, Koji Nakajima

Research Institute of Electrical Communication (RIEC)

Research output: Contribution to journal › Article › peer-review

1 Citation (Scopus)

Abstract

A network based on the Inverse Function Delayed (ID) model which can recall a temporal sequence of patterns, is proposed. The classical problem that the network is forced to make long distance jumps due to strong attractors that have to be isolated from each other, is solved by the introduction of the ID neuron. The ID neuron has negative resistance in its dynamics which makes a gradual change from one attractor to another possible. It is then shown that a network structure consisting of paired conventional and ID neurons, perfectly can recall a sequence.

Original language	English
Pages (from-to)	2818-2824
Number of pages	7
Journal	IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
Volume	E89-A
Issue number	10
DOIs	https://doi.org/10.1093/ietfec/e89-a.10.2818
Publication status	Published - 2006 Oct

Keywords

Inverse function delayed model
Negative resistance
Temporal sequences of patterns

ASJC Scopus subject areas

Signal Processing
Computer Graphics and Computer-Aided Design
Electrical and Electronic Engineering
Applied Mathematics

Access to Document

10.1093/ietfec/e89-a.10.2818

Fingerprint Dive into the research topics of 'Temporal sequences of patterns with an inverse function delayed Neural network'. Together they form a unique fingerprint.

Cite this

@article{572f26915a76497ca8bd800ded1f197e,

title = "Temporal sequences of patterns with an inverse function delayed Neural network",

abstract = "A network based on the Inverse Function Delayed (ID) model which can recall a temporal sequence of patterns, is proposed. The classical problem that the network is forced to make long distance jumps due to strong attractors that have to be isolated from each other, is solved by the introduction of the ID neuron. The ID neuron has negative resistance in its dynamics which makes a gradual change from one attractor to another possible. It is then shown that a network structure consisting of paired conventional and ID neurons, perfectly can recall a sequence.",

keywords = "Inverse function delayed model, Negative resistance, Temporal sequences of patterns",

author = "Johan Sveholm and Yoshihiro Hayakawa and Koji Nakajima",

year = "2006",

month = oct,

doi = "10.1093/ietfec/e89-a.10.2818",

language = "English",

volume = "E89-A",

pages = "2818--2824",

journal = "IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences",

issn = "0916-8508",

publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",

number = "10",

}

TY - JOUR

T1 - Temporal sequences of patterns with an inverse function delayed Neural network

AU - Sveholm, Johan

AU - Hayakawa, Yoshihiro

AU - Nakajima, Koji

PY - 2006/10

Y1 - 2006/10

N2 - A network based on the Inverse Function Delayed (ID) model which can recall a temporal sequence of patterns, is proposed. The classical problem that the network is forced to make long distance jumps due to strong attractors that have to be isolated from each other, is solved by the introduction of the ID neuron. The ID neuron has negative resistance in its dynamics which makes a gradual change from one attractor to another possible. It is then shown that a network structure consisting of paired conventional and ID neurons, perfectly can recall a sequence.

AB - A network based on the Inverse Function Delayed (ID) model which can recall a temporal sequence of patterns, is proposed. The classical problem that the network is forced to make long distance jumps due to strong attractors that have to be isolated from each other, is solved by the introduction of the ID neuron. The ID neuron has negative resistance in its dynamics which makes a gradual change from one attractor to another possible. It is then shown that a network structure consisting of paired conventional and ID neurons, perfectly can recall a sequence.

KW - Inverse function delayed model

KW - Negative resistance

KW - Temporal sequences of patterns

UR - http://www.scopus.com/inward/record.url?scp=33750086682&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33750086682&partnerID=8YFLogxK

U2 - 10.1093/ietfec/e89-a.10.2818

DO - 10.1093/ietfec/e89-a.10.2818

M3 - Article

AN - SCOPUS:33750086682

VL - E89-A

SP - 2818

EP - 2824

JO - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

JF - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

SN - 0916-8508

IS - 10

ER -