Neural Cognitive Maps (NCMs)

Takanobu Obata, Masafumi Hagiwara

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

3 Citations (Scopus)

Abstract

In this paper, we propose novel Cognitive Maps using neural networks named Neural Cognitive Maps (NCMs). Owing to the usage of neural networks, the modeling and prediction abilities of the NCMs are greatly improved compared with those of the conventional FCMs. In order to treat time series inputs effectively, each network receives the latest and the past outputs from all of the networks and is trained by backpropagation algorithm. In addition, a novel pruning method is employed to eliminate useless nodes and weights in each neural network. The pruning has two important effects: one is to improve the performance of the neural network; the other is to give useful information for users to estimate causal relations from the pruned neural network. Computer simulation results indicate the validity and effectiveness of the proposed NCMs.

Original languageEnglish
Title of host publicationProceedings of the IEEE International Conference on Systems, Man and Cybernetics
PublisherIEEE
Pages3337-3342
Number of pages6
Volume4
Publication statusPublished - 1997
EventProceedings of the 1997 IEEE International Conference on Systems, Man, and Cybernetics. Part 3 (of 5) - Orlando, FL, USA
Duration: 1997 Oct 121997 Oct 15

Other

OtherProceedings of the 1997 IEEE International Conference on Systems, Man, and Cybernetics. Part 3 (of 5)
CityOrlando, FL, USA
Period97/10/1297/10/15

Fingerprint

Neural networks
Backpropagation algorithms
Time series
Computer simulation

ASJC Scopus subject areas

  • Hardware and Architecture
  • Control and Systems Engineering

Cite this

Obata, T., & Hagiwara, M. (1997). Neural Cognitive Maps (NCMs). In Proceedings of the IEEE International Conference on Systems, Man and Cybernetics (Vol. 4, pp. 3337-3342). IEEE.

Neural Cognitive Maps (NCMs). / Obata, Takanobu; Hagiwara, Masafumi.

Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. Vol. 4 IEEE, 1997. p. 3337-3342.

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

Obata, T & Hagiwara, M 1997, Neural Cognitive Maps (NCMs). in Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. vol. 4, IEEE, pp. 3337-3342, Proceedings of the 1997 IEEE International Conference on Systems, Man, and Cybernetics. Part 3 (of 5), Orlando, FL, USA, 97/10/12.
Obata T, Hagiwara M. Neural Cognitive Maps (NCMs). In Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. Vol. 4. IEEE. 1997. p. 3337-3342
Obata, Takanobu ; Hagiwara, Masafumi. / Neural Cognitive Maps (NCMs). Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. Vol. 4 IEEE, 1997. pp. 3337-3342
@inproceedings{b72c7a42d83646ef9d71fa282378e8d4,
title = "Neural Cognitive Maps (NCMs)",
abstract = "In this paper, we propose novel Cognitive Maps using neural networks named Neural Cognitive Maps (NCMs). Owing to the usage of neural networks, the modeling and prediction abilities of the NCMs are greatly improved compared with those of the conventional FCMs. In order to treat time series inputs effectively, each network receives the latest and the past outputs from all of the networks and is trained by backpropagation algorithm. In addition, a novel pruning method is employed to eliminate useless nodes and weights in each neural network. The pruning has two important effects: one is to improve the performance of the neural network; the other is to give useful information for users to estimate causal relations from the pruned neural network. Computer simulation results indicate the validity and effectiveness of the proposed NCMs.",
author = "Takanobu Obata and Masafumi Hagiwara",
year = "1997",
language = "English",
volume = "4",
pages = "3337--3342",
booktitle = "Proceedings of the IEEE International Conference on Systems, Man and Cybernetics",
publisher = "IEEE",

}

TY - GEN

T1 - Neural Cognitive Maps (NCMs)

AU - Obata, Takanobu

AU - Hagiwara, Masafumi

PY - 1997

Y1 - 1997

N2 - In this paper, we propose novel Cognitive Maps using neural networks named Neural Cognitive Maps (NCMs). Owing to the usage of neural networks, the modeling and prediction abilities of the NCMs are greatly improved compared with those of the conventional FCMs. In order to treat time series inputs effectively, each network receives the latest and the past outputs from all of the networks and is trained by backpropagation algorithm. In addition, a novel pruning method is employed to eliminate useless nodes and weights in each neural network. The pruning has two important effects: one is to improve the performance of the neural network; the other is to give useful information for users to estimate causal relations from the pruned neural network. Computer simulation results indicate the validity and effectiveness of the proposed NCMs.

AB - In this paper, we propose novel Cognitive Maps using neural networks named Neural Cognitive Maps (NCMs). Owing to the usage of neural networks, the modeling and prediction abilities of the NCMs are greatly improved compared with those of the conventional FCMs. In order to treat time series inputs effectively, each network receives the latest and the past outputs from all of the networks and is trained by backpropagation algorithm. In addition, a novel pruning method is employed to eliminate useless nodes and weights in each neural network. The pruning has two important effects: one is to improve the performance of the neural network; the other is to give useful information for users to estimate causal relations from the pruned neural network. Computer simulation results indicate the validity and effectiveness of the proposed NCMs.

UR - http://www.scopus.com/inward/record.url?scp=0031353447&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031353447&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0031353447

VL - 4

SP - 3337

EP - 3342

BT - Proceedings of the IEEE International Conference on Systems, Man and Cybernetics

PB - IEEE

ER -