Heuristic configuration of single hidden-layer feed-forward neural networks

✍ Scribed by Nitin Indurkhya; Sholom M. Weiss

• Book ID: 104625389
• Publisher: Springer US
• Year: 1992
• Tongue: English
• Weight: 590 KB
• Volume: 2
• Category: Article
• ISSN: 0924-669X
• DOI: 10.1007/bf00058649

✦ Synopsis

For optimum statistical classification and generalization with single hidden-layer neural network models, two tasks must be performed: (a) learning the best set of weights for a network of k hidden units and (b) determining k, the best complexity fit. We contrast two approaches to construction of neural network classifiers: (a) standard back-propagation as applied to a series of single hidden-layer feed-forward neural networks with differing number of hidden units and (b) a heuristic cascade-correlation approach that quickly and dynamically configures the hidden units in a network and learns the best set of weights for it. Four real-world applications are considered. On these examples, the backpropagation approach yielded somewhat better results, but with far greater computation times. The best complexity fit, k, for both approaches were quite similar. This suggests a hybrid approach to c.onstructing single hidden-layer feed-forward neural network classifiers in which the number of hidden units is determined by cascade-correlation and the weights are learned by back-propagation.