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

Full Text Views

0

Share
Cite this

Summary :

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.

Publication: IEICE TRANSACTIONS on Fundamentals Vol.E89-A No.10 pp.2818-2824

Publication Date: 2006/10/01

Publicized

Online ISSN: 1745-1337

DOI: 10.1093/ietfec/e89-a.10.2818

Type of Manuscript: Special Section PAPER (Special Section on Nonlinear Theory and its Applications)

Category: Control, Neural Networks and Learning

Cite this

Copy

Johan SVEHOLM, Yoshihiro HAYAKAWA, Koji NAKAJIMA, "Temporal Sequences of Patterns with an Inverse Function Delayed Neural Network" in IEICE TRANSACTIONS on Fundamentals, vol. E89-A, no. 10, pp. 2818-2824, October 2006, doi: 10.1093/ietfec/e89-a.10.2818.
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.
URL: https://globals.ieice.org/en_transactions/fundamentals/10.1093/ietfec/e89-a.10.2818/_p

Copy

@ARTICLE{e89-a_10_2818,
author={Johan SVEHOLM, Yoshihiro HAYAKAWA, Koji NAKAJIMA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Temporal Sequences of Patterns with an Inverse Function Delayed Neural Network},
year={2006},
volume={E89-A},
number={10},
pages={2818-2824},
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={},
doi={10.1093/ietfec/e89-a.10.2818},
ISSN={1745-1337},
month={October},}

Copy

TY - JOUR
TI - Temporal Sequences of Patterns with an Inverse Function Delayed Neural Network
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 2818
EP - 2824
AU - Johan SVEHOLM
AU - Yoshihiro HAYAKAWA
AU - Koji NAKAJIMA
PY - 2006
DO - 10.1093/ietfec/e89-a.10.2818
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E89-A
IS - 10
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - October 2006
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.
ER -