Learning Petri network with route control

Kotaro Hirasawa, Seiji Oka, Shingo Sakai, Masanao Obayashi, Junichi Murata

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

Large-scale complicated systems are required to be controlled timely and appropriately. A human brain has similar functions to those of a controller of the large-scale complicated systems; it scans and recognizes sensory inputs and outputs responses to the environments. Why does a human brain work skillfully? The key is the capability of functions distribution and learning. Functions distribution means that a specific part exists in the brain, in order to realize a specific function. For example, a live neural network has different acting parts corresponding to different network inputs or stimuli. In this paper, we have proposed a new brain-like model that we call Learning Petri Network(L.P.N.). The fundamental idea is to revise Petri Net. Petri Net is composed of state and transition and can control firing by tokens, so it is possible for this net to realize functions distribution. The revising point is to give Petri Net the ability of learning as Neural Network(N.N.). And, it is the fundamental difference from N.N., that learning of the proposed method is carried out on the only network pass of the token transfer.

Original languageEnglish
Pages (from-to)2076-2711
Number of pages636
JournalUnknown Journal
Volume3
Publication statusPublished - 1995

Fingerprint

brain
Brain
learning
Petri nets
Distribution functions
Neural networks
Large scale systems
Controllers
distribution

All Science Journal Classification (ASJC) codes

  • Hardware and Architecture
  • Control and Systems Engineering

Cite this

Hirasawa, K., Oka, S., Sakai, S., Obayashi, M., & Murata, J. (1995). Learning Petri network with route control. Unknown Journal, 3, 2076-2711.

Learning Petri network with route control. / Hirasawa, Kotaro; Oka, Seiji; Sakai, Shingo; Obayashi, Masanao; Murata, Junichi.

In: Unknown Journal, Vol. 3, 1995, p. 2076-2711.

Research output: Contribution to journalArticle

Hirasawa, K, Oka, S, Sakai, S, Obayashi, M & Murata, J 1995, 'Learning Petri network with route control', Unknown Journal, vol. 3, pp. 2076-2711.
Hirasawa K, Oka S, Sakai S, Obayashi M, Murata J. Learning Petri network with route control. Unknown Journal. 1995;3:2076-2711.
Hirasawa, Kotaro ; Oka, Seiji ; Sakai, Shingo ; Obayashi, Masanao ; Murata, Junichi. / Learning Petri network with route control. In: Unknown Journal. 1995 ; Vol. 3. pp. 2076-2711.
@article{36d2e79ea20542c9b03c54b5533b252d,
title = "Learning Petri network with route control",
abstract = "Large-scale complicated systems are required to be controlled timely and appropriately. A human brain has similar functions to those of a controller of the large-scale complicated systems; it scans and recognizes sensory inputs and outputs responses to the environments. Why does a human brain work skillfully? The key is the capability of functions distribution and learning. Functions distribution means that a specific part exists in the brain, in order to realize a specific function. For example, a live neural network has different acting parts corresponding to different network inputs or stimuli. In this paper, we have proposed a new brain-like model that we call Learning Petri Network(L.P.N.). The fundamental idea is to revise Petri Net. Petri Net is composed of state and transition and can control firing by tokens, so it is possible for this net to realize functions distribution. The revising point is to give Petri Net the ability of learning as Neural Network(N.N.). And, it is the fundamental difference from N.N., that learning of the proposed method is carried out on the only network pass of the token transfer.",
author = "Kotaro Hirasawa and Seiji Oka and Shingo Sakai and Masanao Obayashi and Junichi Murata",
year = "1995",
language = "English",
volume = "3",
pages = "2076--2711",
journal = "Quaternary International",
issn = "1040-6182",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Learning Petri network with route control

AU - Hirasawa, Kotaro

AU - Oka, Seiji

AU - Sakai, Shingo

AU - Obayashi, Masanao

AU - Murata, Junichi

PY - 1995

Y1 - 1995

N2 - Large-scale complicated systems are required to be controlled timely and appropriately. A human brain has similar functions to those of a controller of the large-scale complicated systems; it scans and recognizes sensory inputs and outputs responses to the environments. Why does a human brain work skillfully? The key is the capability of functions distribution and learning. Functions distribution means that a specific part exists in the brain, in order to realize a specific function. For example, a live neural network has different acting parts corresponding to different network inputs or stimuli. In this paper, we have proposed a new brain-like model that we call Learning Petri Network(L.P.N.). The fundamental idea is to revise Petri Net. Petri Net is composed of state and transition and can control firing by tokens, so it is possible for this net to realize functions distribution. The revising point is to give Petri Net the ability of learning as Neural Network(N.N.). And, it is the fundamental difference from N.N., that learning of the proposed method is carried out on the only network pass of the token transfer.

AB - Large-scale complicated systems are required to be controlled timely and appropriately. A human brain has similar functions to those of a controller of the large-scale complicated systems; it scans and recognizes sensory inputs and outputs responses to the environments. Why does a human brain work skillfully? The key is the capability of functions distribution and learning. Functions distribution means that a specific part exists in the brain, in order to realize a specific function. For example, a live neural network has different acting parts corresponding to different network inputs or stimuli. In this paper, we have proposed a new brain-like model that we call Learning Petri Network(L.P.N.). The fundamental idea is to revise Petri Net. Petri Net is composed of state and transition and can control firing by tokens, so it is possible for this net to realize functions distribution. The revising point is to give Petri Net the ability of learning as Neural Network(N.N.). And, it is the fundamental difference from N.N., that learning of the proposed method is carried out on the only network pass of the token transfer.

UR - http://www.scopus.com/inward/record.url?scp=0029546146&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029546146&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0029546146

VL - 3

SP - 2076

EP - 2711

JO - Quaternary International

JF - Quaternary International

SN - 1040-6182

ER -