Feed-forward network with one hidden layer and their rates of approximation

Feed-forward network with one hidden layer and their rates of approximation

Abstract

We present an overview of some rates of approximation with respect to various computational units in the hidden layer of a one-layered feed-forward neu-ral network. The problem of estimating the number of units in the hidden layer is examined to ensure a given degree of approximation for a given function class. The results are discussed in terms of their complexity and functional characteristics.

Grafik Top
Authors
  • Hlavackova-Schindler, Katerina
Grafik Top
Shortfacts
Category
Paper in Conference Proceedings or in Workshop Proceedings (Paper)
Event Title
UKACC International Conference on CONTROL ‘98
Divisions
Data Mining and Machine Learning
Subjects
Kuenstliche Intelligenz
Event Location
Swansea, United Kingdom
Event Type
Conference
Event Dates
1-4 September, 1998
Series Name
Proceedings of UKACC International Conference on CONTROL ‘98
ISSN/ISBN
085296708X
Page Range
pp. 727-733
Date
1998
Export
Grafik Top