Es. Tzafestas et al., Performance evaluation and dynamic node generation criteria for 'principalcomponent analysis' neural networks, MATH COMP S, 51(3-4), 2000, pp. 145-156
This paper is concerned with the solution of the principal component analys
is (PCA) problem with the aid of neural networks (NNs). After an overview o
f the basic NN-based PCA concepts and a listing of the available algorithms
, two criteria for evaluating PCA NN algorithms are proposed. Then, a new c
riterion for the generation of improved PCA NN structures with reduced size
is presented. Using this criterion, one can start with a small network and
dynamically add new nodes at the hidden layer(s) during training, one at a
time, until the desired performance is achieved. A simulation example is p
rovided that shows the applicability and effectiveness of the methodology (
C) 2000 IMACS/Elsevier Science B.V. All rights reserved.