Self-organization in probabilistic neural networks

Yuhki Shiraishi, Kotaro Hirasawa, Jinglu Hu, Junichi Murata

Research output: Contribution to journalArticle

Abstract

S. A. Kauffman explored the law of self-organization in random Boolean networks, and K. Inagaki also did it in neural networks partially. The aim of this paper is to show that probabilistic neural networks (PNNs) hold the order, even though the weights, the thresholds, and the connections between neurons are determined randomly; where PNNs are recurrent networks and controlled by a probabilistic transition rule based on a Boltzmann machine. In addition, the deterministic transient neural networks (DNNs) which are the special networks of PNNs are studied extensively. From simulations, it is shown that in DNNs the dynamics follow the square-root law and there is another new critical point as for the distribution of the thresholds. In addition, it is shown that in PNNs the averages of the Hamming distance between the attractors of DNN and PNN stay around a certain value depending on the thresholds and the gradient of the Sigmoidal function. These results can be explained by the sensitivity to the initial conditions of DNNs.

Original languageEnglish
Pages (from-to)2533-2538
Number of pages6
JournalUnknown Journal
Volume4
Publication statusPublished - 2000

Fingerprint

self organization
Neural networks
simulation
Hamming distance
Recurrent neural networks
Neurons

All Science Journal Classification (ASJC) codes

  • Hardware and Architecture
  • Control and Systems Engineering

Cite this

Shiraishi, Y., Hirasawa, K., Hu, J., & Murata, J. (2000). Self-organization in probabilistic neural networks. Unknown Journal, 4, 2533-2538.

Self-organization in probabilistic neural networks. / Shiraishi, Yuhki; Hirasawa, Kotaro; Hu, Jinglu; Murata, Junichi.

In: Unknown Journal, Vol. 4, 2000, p. 2533-2538.

Research output: Contribution to journalArticle

Shiraishi, Y, Hirasawa, K, Hu, J & Murata, J 2000, 'Self-organization in probabilistic neural networks', Unknown Journal, vol. 4, pp. 2533-2538.
Shiraishi Y, Hirasawa K, Hu J, Murata J. Self-organization in probabilistic neural networks. Unknown Journal. 2000;4:2533-2538.
Shiraishi, Yuhki ; Hirasawa, Kotaro ; Hu, Jinglu ; Murata, Junichi. / Self-organization in probabilistic neural networks. In: Unknown Journal. 2000 ; Vol. 4. pp. 2533-2538.
@article{bec4f719ed7a4fba968d0803352e999a,
title = "Self-organization in probabilistic neural networks",
abstract = "S. A. Kauffman explored the law of self-organization in random Boolean networks, and K. Inagaki also did it in neural networks partially. The aim of this paper is to show that probabilistic neural networks (PNNs) hold the order, even though the weights, the thresholds, and the connections between neurons are determined randomly; where PNNs are recurrent networks and controlled by a probabilistic transition rule based on a Boltzmann machine. In addition, the deterministic transient neural networks (DNNs) which are the special networks of PNNs are studied extensively. From simulations, it is shown that in DNNs the dynamics follow the square-root law and there is another new critical point as for the distribution of the thresholds. In addition, it is shown that in PNNs the averages of the Hamming distance between the attractors of DNN and PNN stay around a certain value depending on the thresholds and the gradient of the Sigmoidal function. These results can be explained by the sensitivity to the initial conditions of DNNs.",
author = "Yuhki Shiraishi and Kotaro Hirasawa and Jinglu Hu and Junichi Murata",
year = "2000",
language = "English",
volume = "4",
pages = "2533--2538",
journal = "Quaternary International",
issn = "1040-6182",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Self-organization in probabilistic neural networks

AU - Shiraishi, Yuhki

AU - Hirasawa, Kotaro

AU - Hu, Jinglu

AU - Murata, Junichi

PY - 2000

Y1 - 2000

N2 - S. A. Kauffman explored the law of self-organization in random Boolean networks, and K. Inagaki also did it in neural networks partially. The aim of this paper is to show that probabilistic neural networks (PNNs) hold the order, even though the weights, the thresholds, and the connections between neurons are determined randomly; where PNNs are recurrent networks and controlled by a probabilistic transition rule based on a Boltzmann machine. In addition, the deterministic transient neural networks (DNNs) which are the special networks of PNNs are studied extensively. From simulations, it is shown that in DNNs the dynamics follow the square-root law and there is another new critical point as for the distribution of the thresholds. In addition, it is shown that in PNNs the averages of the Hamming distance between the attractors of DNN and PNN stay around a certain value depending on the thresholds and the gradient of the Sigmoidal function. These results can be explained by the sensitivity to the initial conditions of DNNs.

AB - S. A. Kauffman explored the law of self-organization in random Boolean networks, and K. Inagaki also did it in neural networks partially. The aim of this paper is to show that probabilistic neural networks (PNNs) hold the order, even though the weights, the thresholds, and the connections between neurons are determined randomly; where PNNs are recurrent networks and controlled by a probabilistic transition rule based on a Boltzmann machine. In addition, the deterministic transient neural networks (DNNs) which are the special networks of PNNs are studied extensively. From simulations, it is shown that in DNNs the dynamics follow the square-root law and there is another new critical point as for the distribution of the thresholds. In addition, it is shown that in PNNs the averages of the Hamming distance between the attractors of DNN and PNN stay around a certain value depending on the thresholds and the gradient of the Sigmoidal function. These results can be explained by the sensitivity to the initial conditions of DNNs.

UR - http://www.scopus.com/inward/record.url?scp=0034506641&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034506641&partnerID=8YFLogxK

M3 - Article

VL - 4

SP - 2533

EP - 2538

JO - Quaternary International

JF - Quaternary International

SN - 1040-6182

ER -