Title :
Selecting an optimal neural network
Author_Institution :
Orincon Corp., San Diego, CA, USA
Abstract :
A relationship between optimal network design and statistical model identification is described. A derivative of Akaike´s information criterion (AIC) is given. This modification yields an information statistic which can be used to select a best network for binary classification problems objectively. The technique can be extended to problems with an arbitrary number of classes
Keywords :
identification; neural nets; Akaike´s information criterion; binary classification; optimal neural network; statistical model identification; Art; Computational efficiency; Computer networks; Feedforward neural networks; Maximum likelihood estimation; Neural networks; Neurofeedback; Predictive models; Statistics; Training data;
Conference_Titel :
Industrial Electronics Society, 1990. IECON '90., 16th Annual Conference of IEEE
Conference_Location :
Pacific Grove, CA
Print_ISBN :
0-87942-600-4
DOI :
10.1109/IECON.1990.149309
