Recalling Temporal Sequences of Patterns Using Neurons with Hysteretic Property

Johan SVEHOLM; Yoshihiro HAYAKAWA; Koji NAKAJIMA

doi:10.1093/ietfec/e91-a.4.943

Recalling Temporal Sequences of Patterns Using Neurons with Hysteretic Property

Johan SVEHOLM, Yoshihiro HAYAKAWA, Koji NAKAJIMA

Full Text Views

0

Cite this

Summary :

Further development of a network based on the Inverse Function Delayed (ID) model which can recall temporal sequences of patterns, is proposed. Additional advantage is taken of the negative resistance region of the ID model and its hysteretic properties by widening the negative resistance region and letting the output of the ID neuron be almost instant. Calling this neuron limit ID neuron, a model with limit ID neurons connected pairwise with conventional neurons enlarges the storage capacity and increases it even further by using a weightmatrix that is calculated to guarantee the storage after transforming the sequence of patterns into a linear separation problem. The network's tolerance, or the model's ability to recall a sequence, starting in a pattern with initial distortion is also investigated and by choosing a suitable value for the output delay of the conventional neuron, the distortion is gradually reduced and finally vanishes.

Publication: IEICE TRANSACTIONS on Fundamentals Vol.E91-A No.4 pp.943-950

Publication Date: 2008/04/01

Publicized

Online ISSN: 1745-1337

DOI: 10.1093/ietfec/e91-a.4.943

Type of Manuscript: Special Section PAPER (Special Section on Selected Papers from the 20th Workshop on Circuits and Systems in Karuizawa)

Category

Cite this

Copy

Johan SVEHOLM, Yoshihiro HAYAKAWA, Koji NAKAJIMA, "Recalling Temporal Sequences of Patterns Using Neurons with Hysteretic Property" in IEICE TRANSACTIONS on Fundamentals, vol. E91-A, no. 4, pp. 943-950, April 2008, doi: 10.1093/ietfec/e91-a.4.943.
Abstract: Further development of a network based on the Inverse Function Delayed (ID) model which can recall temporal sequences of patterns, is proposed. Additional advantage is taken of the negative resistance region of the ID model and its hysteretic properties by widening the negative resistance region and letting the output of the ID neuron be almost instant. Calling this neuron limit ID neuron, a model with limit ID neurons connected pairwise with conventional neurons enlarges the storage capacity and increases it even further by using a weightmatrix that is calculated to guarantee the storage after transforming the sequence of patterns into a linear separation problem. The network's tolerance, or the model's ability to recall a sequence, starting in a pattern with initial distortion is also investigated and by choosing a suitable value for the output delay of the conventional neuron, the distortion is gradually reduced and finally vanishes.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1093/ietfec/e91-a.4.943/_p

Copy

@ARTICLE{e91-a_4_943,
author={Johan SVEHOLM, Yoshihiro HAYAKAWA, Koji NAKAJIMA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Recalling Temporal Sequences of Patterns Using Neurons with Hysteretic Property},
year={2008},
volume={E91-A},
number={4},
pages={943-950},
abstract={Further development of a network based on the Inverse Function Delayed (ID) model which can recall temporal sequences of patterns, is proposed. Additional advantage is taken of the negative resistance region of the ID model and its hysteretic properties by widening the negative resistance region and letting the output of the ID neuron be almost instant. Calling this neuron limit ID neuron, a model with limit ID neurons connected pairwise with conventional neurons enlarges the storage capacity and increases it even further by using a weightmatrix that is calculated to guarantee the storage after transforming the sequence of patterns into a linear separation problem. The network's tolerance, or the model's ability to recall a sequence, starting in a pattern with initial distortion is also investigated and by choosing a suitable value for the output delay of the conventional neuron, the distortion is gradually reduced and finally vanishes.},
keywords={},
doi={10.1093/ietfec/e91-a.4.943},
ISSN={1745-1337},
month={April},}

Copy

TY - JOUR
TI - Recalling Temporal Sequences of Patterns Using Neurons with Hysteretic Property
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 943
EP - 950
AU - Johan SVEHOLM
AU - Yoshihiro HAYAKAWA
AU - Koji NAKAJIMA
PY - 2008
DO - 10.1093/ietfec/e91-a.4.943
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E91-A
IS - 4
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - April 2008
AB - Further development of a network based on the Inverse Function Delayed (ID) model which can recall temporal sequences of patterns, is proposed. Additional advantage is taken of the negative resistance region of the ID model and its hysteretic properties by widening the negative resistance region and letting the output of the ID neuron be almost instant. Calling this neuron limit ID neuron, a model with limit ID neurons connected pairwise with conventional neurons enlarges the storage capacity and increases it even further by using a weightmatrix that is calculated to guarantee the storage after transforming the sequence of patterns into a linear separation problem. The network's tolerance, or the model's ability to recall a sequence, starting in a pattern with initial distortion is also investigated and by choosing a suitable value for the output delay of the conventional neuron, the distortion is gradually reduced and finally vanishes.
ER -