Performance optimization of function localization neural network by using reinforcement learning

Takafumi Sasakawa, Takayuki Furuzuki, Kotaro Hirasawa

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

According to Hebb's cell assembly theory, the brain has the capability of function localization. On the other hand, it is suggested that the brain has three different learning paradigms: supervised, unsupervised and reinforcement learning. Inspired by the above knowledge of brain, we present a selforganizing function localization neural network (FLNN), that contains supervised, unsupervised and reinforcement learning paradigms. In this paper, we concentrate our discussion mainly on applying a simplified reinforcement learning called evaluative feedback to optimization of the self-organizing FLNN. Numerical simulations show that the self-organizing FLNN has superior performance to an ordinary artificial neural network (ANN).

Original languageEnglish
Title of host publicationProceedings of the International Joint Conference on Neural Networks
Pages1314-1319
Number of pages6
Volume2
DOIs
Publication statusPublished - 2005
EventInternational Joint Conference on Neural Networks, IJCNN 2005 - Montreal, QC
Duration: 2005 Jul 312005 Aug 4

Other

OtherInternational Joint Conference on Neural Networks, IJCNN 2005
CityMontreal, QC
Period05/7/3105/8/4

Fingerprint

Reinforcement learning
Neural networks
Brain
Unsupervised learning
Supervised learning
Feedback
Computer simulation

ASJC Scopus subject areas

  • Software

Cite this

Sasakawa, T., Furuzuki, T., & Hirasawa, K. (2005). Performance optimization of function localization neural network by using reinforcement learning. In Proceedings of the International Joint Conference on Neural Networks (Vol. 2, pp. 1314-1319). [1556044] https://doi.org/10.1109/IJCNN.2005.1556044

Performance optimization of function localization neural network by using reinforcement learning. / Sasakawa, Takafumi; Furuzuki, Takayuki; Hirasawa, Kotaro.

Proceedings of the International Joint Conference on Neural Networks. Vol. 2 2005. p. 1314-1319 1556044.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Sasakawa, T, Furuzuki, T & Hirasawa, K 2005, Performance optimization of function localization neural network by using reinforcement learning. in Proceedings of the International Joint Conference on Neural Networks. vol. 2, 1556044, pp. 1314-1319, International Joint Conference on Neural Networks, IJCNN 2005, Montreal, QC, 05/7/31. https://doi.org/10.1109/IJCNN.2005.1556044
Sasakawa T, Furuzuki T, Hirasawa K. Performance optimization of function localization neural network by using reinforcement learning. In Proceedings of the International Joint Conference on Neural Networks. Vol. 2. 2005. p. 1314-1319. 1556044 https://doi.org/10.1109/IJCNN.2005.1556044
Sasakawa, Takafumi ; Furuzuki, Takayuki ; Hirasawa, Kotaro. / Performance optimization of function localization neural network by using reinforcement learning. Proceedings of the International Joint Conference on Neural Networks. Vol. 2 2005. pp. 1314-1319
@inproceedings{8e3fcd7db6d74f1eadb110b1e7877378,
title = "Performance optimization of function localization neural network by using reinforcement learning",
abstract = "According to Hebb's cell assembly theory, the brain has the capability of function localization. On the other hand, it is suggested that the brain has three different learning paradigms: supervised, unsupervised and reinforcement learning. Inspired by the above knowledge of brain, we present a selforganizing function localization neural network (FLNN), that contains supervised, unsupervised and reinforcement learning paradigms. In this paper, we concentrate our discussion mainly on applying a simplified reinforcement learning called evaluative feedback to optimization of the self-organizing FLNN. Numerical simulations show that the self-organizing FLNN has superior performance to an ordinary artificial neural network (ANN).",
author = "Takafumi Sasakawa and Takayuki Furuzuki and Kotaro Hirasawa",
year = "2005",
doi = "10.1109/IJCNN.2005.1556044",
language = "English",
isbn = "0780390482",
volume = "2",
pages = "1314--1319",
booktitle = "Proceedings of the International Joint Conference on Neural Networks",

}

TY - GEN

T1 - Performance optimization of function localization neural network by using reinforcement learning

AU - Sasakawa, Takafumi

AU - Furuzuki, Takayuki

AU - Hirasawa, Kotaro

PY - 2005

Y1 - 2005

N2 - According to Hebb's cell assembly theory, the brain has the capability of function localization. On the other hand, it is suggested that the brain has three different learning paradigms: supervised, unsupervised and reinforcement learning. Inspired by the above knowledge of brain, we present a selforganizing function localization neural network (FLNN), that contains supervised, unsupervised and reinforcement learning paradigms. In this paper, we concentrate our discussion mainly on applying a simplified reinforcement learning called evaluative feedback to optimization of the self-organizing FLNN. Numerical simulations show that the self-organizing FLNN has superior performance to an ordinary artificial neural network (ANN).

AB - According to Hebb's cell assembly theory, the brain has the capability of function localization. On the other hand, it is suggested that the brain has three different learning paradigms: supervised, unsupervised and reinforcement learning. Inspired by the above knowledge of brain, we present a selforganizing function localization neural network (FLNN), that contains supervised, unsupervised and reinforcement learning paradigms. In this paper, we concentrate our discussion mainly on applying a simplified reinforcement learning called evaluative feedback to optimization of the self-organizing FLNN. Numerical simulations show that the self-organizing FLNN has superior performance to an ordinary artificial neural network (ANN).

UR - http://www.scopus.com/inward/record.url?scp=33745964360&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33745964360&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2005.1556044

DO - 10.1109/IJCNN.2005.1556044

M3 - Conference contribution

SN - 0780390482

SN - 9780780390485

VL - 2

SP - 1314

EP - 1319

BT - Proceedings of the International Joint Conference on Neural Networks

ER -