Self-organization in probabilistic neural networks

Yuhki Shiraishi*, Kotaro Hirasawa, Jinglu Hu, Junichi Murata

*Corresponding author for this work

Research output: Contribution to journalConference articlepeer-review


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
JournalProceedings of the IEEE International Conference on Systems, Man and Cybernetics
Publication statusPublished - 2000 Dec 1
Externally publishedYes
Event2000 IEEE International Conference on Systems, Man and Cybernetics - Nashville, TN, USA
Duration: 2000 Oct 82000 Oct 11

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Hardware and Architecture


Dive into the research topics of 'Self-organization in probabilistic neural networks'. Together they form a unique fingerprint.

Cite this