The Transactions of the Korean Institute of Electrical Engineers A (대한전기학회논문지:전력기술부문A)

The Korean Institute of Electrical Engineers (대한전기학회)
권호 표지

A Study on the Structure Optimization of Multilayer Neural Networks using Rough Set Theory

러프집합을 이용한 다층 신경망의 구조최적화에 관한 연구

  • Published : 1999.02.01
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we propose a new structure optimization method of multilayer neural networks which begin and carry out learning from a bigger network. This method redundant links and neurons according to the rough set theory. In order to find redundant links, we analyze the variations of all weights and output errors in every step of the learning process, and then make the decision table from their variation of weights and output errors. We can find the redundant links from the initial structure by analyzing the decision table using the rough set theory. This enables us to build a structure as compact as possible, and also enables mapping between input and output. We show the validity and effectiveness of the proposed algorithm by applying it to the XOR problem.

Keywords

References

  1. Introduction to Artificial Neural Systems Jacek M. Zurada
  2. 計測自動制御學會論文集 v.33 no.11 ファジィ推論を用いたニュ-ラルネシトワ-クの構造學習アルゴリズム 有澤正樹;和多田淳三
  3. Proc. of the third Int`l Conf. on Genetic Algorithms and Their Applications Designing neural networks using genetic algorithms G. F. Miller;P. M. Todd;S. U. Hegde
  4. Proc. of the third Int'l Conf. on Genetic Algorithms and Their Applications Toward the genetic synthesis of neural networks S. A. Harp;T. Samad;A. Guba
  5. Artificial Intelligence and Creativity The evolution of connectionist networks X. Yao
  6. International Journal of Computer and Information Science v.11 Rough Sets Pawlak. Z.
  7. Rough Sets : Theoretical Aspects of Reasoning about Data Pawlak. Z.