Skip to main content
Log in

NNF and NNPrF — Fuzzy Petri Nets based on neural network for knowledge representation, reasoning and learning

  • Published:
Journal of Computer Science and Technology Aims and scope Submit manuscript

Abstract

This paper proposes NNF — a fuzzy Petri Net system based on neural network for proposition logic representation, and gives the formal definition of NNF. For the NNF model, forward reasoning algorithm, backward reasoning algorithm and knowledge learning algorithm are discussed based on weight training algorithm of neural network — Back Propagation algorithm.Thus NNF is endowed with the ability of learning a rule. The paper concludes with a discussion on extending NNF to predicate logic, forming NNPrF, and proposing the formal definition and a reasoning algorithm of NNPrF.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Looney C. Fuzzy Petri nets for rule-based decision making.IEEE Trans. on Syst., Man., 1988, (Jan.): 178–183.

    Article  Google Scholar 

  2. Peterka G, Murata T. Proof procedure and answer extraction in Petri net model of logic programs.IEEE Trans. on Software Engineering, 1989, 15(2): 209–217.

    Article  MATH  MathSciNet  Google Scholar 

  3. Lin Chuang. Application of Petri nets to logical inference of HORN clauses.Journal of Software, 1993, 4(4): 33–37.

    Google Scholar 

  4. Zhou Yi, Wu Shilin. The new ways of logic inference of Petri net based on resolution refutation. (accepted byChinese Journal of Computers)

  5. Shen Qing, Tang Lin. The Introduction of Pattern Recognition. Press of the University of National Defense Science and Technology, May 1995.

  6. He Xingui. Knowledge Processing and Expert System. Press of National Defense Industry, Sep. 1990.

Download references

Author information

Authors and Affiliations

Authors

Additional information

Research supported by the National High-Tech R/D Programme of China.

Zhou Yi received her B.S. degree from Computer Science Department of Fudan University in 1993. She is currently pursuing her M.S. degree in computer science from Fudan University. Her main research interests include knowledge representation and reasoning, machine learning, computer network, theory of Petri nets and its applications.

Wu Shilin graduated from Mathematical Department, Fudan University in 1957. He is now a Professor of Department of Computer Science, Fudan University. At present, he is the Vice President of Petri Net Community, Chinese Computer Federation. The areas of his research cover computer communication, computer network, theory of Petri net and its applications.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Zhou, Y., Wu, S. NNF and NNPrF — Fuzzy Petri Nets based on neural network for knowledge representation, reasoning and learning. J. of Comput. Sci. & Technol. 11, 133–149 (1996). https://doi.org/10.1007/BF02943529

Download citation

  • Received:

  • Revised:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF02943529

Keywords

Navigation