Are Multilayer Perceptrons Adequate for Pattern Recognition and Verification?
This paper discusses the ability of multilayer perceptrons (MLP) to model the probability distributions of the inputs in typical pattern recognition problems. It is shown that multilayer perceptrons may be unable to model patterns distributed in typical clusters, since in most practical cases these networks draw open separation surfaces in the pattern space. Unlike multilayer perceptrons, autoassociators and radial basis function networks (RBF) create closed separation surfaces. This make them more suitable especially for pattern verification, but also for dealing with large pattern recognition problems with many classes, where modular structures are typically used.
KeywordsRadial Basis Function Hide Neuron Radial Basis Function Network Multilayer Perceptrons Hide Unit
Unable to display preview. Download preview PDF.
- A. FVosini, M. Gori, and P. Priani. A neural network-based model for paper currency recognition and verification. IEEE Transactions on Neural Networks; 1996.To appearGoogle Scholar
- M. Gori, L. Lastrucci, and G. Soda. Autoassociator-based models for speaker verification. Pattern Recognition Letters, 1996. To appear.Google Scholar