An evolutionary mutation-based algorithm for weight training in neural networks for telecommunication flow modelling

An evolutionary mutation-based algorithm for weight training in neural networks for telecommunication flow modelling

Abstract

Training of perceptron networks with sigmoidal activation functions is executed by a new evolutionary algorithm, Differential Evolution (DE). On this evolutionary optimization method, we apply a search space reduction algorithm and compare this approach to training by standard DE and training by the conjugate gradient method. The testbed is Austrian interregional telecommunication traffic data. In our experiments, DE with only mutation was able to achieve better suboptimal solutions than DE together with crossover and search space reduction. DE with mutation only outperforms the conjugate gradient method in terms of in-sample and out-of-sample performance. The experimental results support the hypothesis that mutation-based evolutionary algorithms (like DE) tend to be more suitable methods for training perceptron networks than crossover-based evolutionary algorithms and gradient based methods. An evolutionary mutation-based algorithm for weight training in neural networks for telecommunication flow modelling.

Grafik Top
Authors
  • Fischer, M.M.
  • Hlavackova-Schindler, Katerina
  • Reismann, Martin
Grafik Top
Editors
  • Mohammadian, M.
Grafik Top
  • Metadata Copyright the British Library Board and other contributors
Grafik Top
Shortfacts
Category
Book Section/Chapter
Divisions
Data Mining and Machine Learning
Subjects
Kuenstliche Intelligenz
Title of Book
CONCURRENT SYSTEMS ENGINEERING SERIES
ISSN/ISBN
905199477X
Page Range
pp. 54-59
Date
1999
Export
Grafik Top