Heuristic configuration of single hidden
β
Nitin Indurkhya; Sholom M. Weiss
π
Article
π
1992
π
Springer US
π
English
β 590 KB
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 ne