Premium
Comparing neural network approximations for different functional forms
Author(s) -
Morgan Peter,
Curry Bruce,
Bey Malcolm
Publication year - 1999
Publication title -
expert systems
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.365
H-Index - 38
eISSN - 1468-0394
pISSN - 0266-4720
DOI - 10.1111/1468-0394.00096
Subject(s) - computer science , generalization , property (philosophy) , artificial neural network , set (abstract data type) , feedforward neural network , feed forward , artificial intelligence , machine learning , theoretical computer science , mathematics , mathematical analysis , philosophy , epistemology , control engineering , engineering , programming language
This paper examines the capacity of feedforward neural networks (NNs) to approximate certain functional forms. Its purpose is to show that the theoretical property of ‘universal approximation’, which provides the basic rationale behind the NN approach, should not be interpreted too literally. The most important issue considered involves the number of hidden layers in the network. We show that for a number of interesting functional forms better generalization is possible with more than one hidden layer, despite theoretical results to the contrary. Our experiments constitute a useful set of counter‐examples.