A hierarchy neural network approach to symbolic logic-algorithms of problem solving

Author

Shuai, Dianxun ; Watanabe, Yoichiro

Author_Institution

Dept. of Electron., Doshisha Univ., Kyoto, Japan

Volume

2

fYear

1993

fDate

25-29 Oct. 1993

Firstpage

1606

Abstract

This paper presents a neural network approach, based on high-order two-dimension temporal and dynamically clustering competitive activation mechanism, to implement the parallel searching algorithm and many other symbolic logic algorithms. This approach is superior in many respects to both the common sequential algorithms of symbolic logic and the common neural network used for optimization problems. Simulations for some problem solving prove the effect of the approach.

Keywords

hierarchical systems; neural nets; optimisation; parallel algorithms; problem solving; search problems; 2D temporal activation mechanism; dynamically clustering competitive activation mechanism; hierarchy neural network; parallel searching algorithm; problem solving; symbolic logic algorithms; symbolic logic-algorithms; Artificial neural networks; Clustering algorithms; Dynamic programming; Logic programming; Machine learning; Machine learning algorithms; Neural networks; Parallel algorithms; Problem-solving; Reflection;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1993. IJCNN '93-Nagoya. Proceedings of 1993 International Joint Conference on

Print_ISBN

0-7803-1421-2

Type

conf

DOI

10.1109/IJCNN.1993.716918

Filename

716918