Abstract
Two criteria are given in this article, one based on the final prediction error technique and another based on maximizing the posterior probability, to determine the node number of one-hidden layer neural network models. These criteria have been directed to find optimal node number of neural network models that gives the smallest value of a validity measure or the maximum of a posterior probability.
Full Text 
Sign-in/Register to access full text options
Sign-in/Register to access full text options 
Paper version not known
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
