Application of Parallel Decomposition for Creation of Reduced Feed-Forward Neural Networks

Authors:
Jacek Lewandowski;Mariusz Rawski;Henryk Rybinski
Affiliations:
ICS, Warsaw University of Technology,;IT, Warsaw University of Technology, Nowowiejska 15/19, 00-665 Warsaw, Poland;ICS, Warsaw University of Technology,
Venue:
RSEISP '07 Proceedings of the international conference on Rough Sets and Intelligent Systems Paradigms
Year:
2007

Citing 4
Cited 0

Foundations of Neural Networks, Fuzzy Systems, and Knowledge Engineering

Foundations of Neural Networks, Fuzzy Systems, and Knowledge Engineering
Rough Sets: Theoretical Aspects of Reasoning about Data

Rough Sets: Theoretical Aspects of Reasoning about Data
An Implementation of Decomposition Algorithm and its Application in Information System Analysis and Logic Synthesis

RSKD '93 Proceedings of the International Workshop on Rough Sets and Knowledge Discovery: Rough Sets, Fuzzy Sets and Knowledge Discovery
Neural Networks: A Comprehensive Foundation (3rd Edition)

Neural Networks: A Comprehensive Foundation (3rd Edition)

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper a method of creating layers of feed-forward neural network that does not need to be learned is presented. Described approach is based on algorithms used in synthesis of logic circuits. Experimental results presented in the paper prove that this method may significantly decrease the time of learning process, increase generalization ability and decrease a probability of sticking in a local minimum. Further work and goals to achieve are also discussed.