Access Restriction

Author Mandischer, Martin
Source CiteSeerX
Content type Text
Publisher IEEE Press, Piscataway NJ
File Format PDF
Language English
Subject Domain (in DDC) Computer science, information & general works ♦ Data processing & computer science
Subject Keyword Noise Resistance ♦ Evolutionary Approach ♦ Genetic Operator ♦ Recent Work ♦ Performance Criterion ♦ Non-binary Encoding ♦ Np-complete Problem ♦ Generalization Ability ♦ Lin Vitter ♦ Function Approximation ♦ Time-series Domain ♦ Evolutionary Algorithm ♦ Optimal Network Topology ♦ Neural Network ♦ Recurrent Neural Network ♦ Real World Task ♦ Data-structure-based Genotypic Network Representation ♦ Fixed Point
Description This paper presents an evolutionary approach for the design of feed-forward and recurrent neural networks. We show that Evolutionary Algorithms can be used for the construction of networks for real world tasks. Therefore, a data-structure-based genotypic network representation, as well as genetic operators, are introduced. Results from the classification, function approximation and time-series domain are presented. 1. Introduction The performance of neural networks highly depends on the architecture of the networks and their parameters. Therefore, determeing the architecture of a network (size, structure, connectivity) greatly affects the performance criteria, i.e. learning speed, accuracy of learning, noise resistance, stability of fixed points and generalization ability. Recent works of Judd and Lin/Vitter show that learning in general, as well as choosing an optimal network topology, are NP-complete problems [8, 9]. They also have shown that placing constraints on the topology can...
Educational Role Student ♦ Teacher
Age Range above 22 year
Educational Use Research
Education Level UG and PG ♦ Career/Technical Study
Learning Resource Type Article
Publisher Date 1995-01-01
Publisher Institution In Proceedings of the 2nd IEEE Conference on Evolutionary Computation (ICEC