By Topic

Training of a feedforward multiple-valued neural network by error backpropagation with a multilevel threshold function

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

The purchase and pricing options are temporarily unavailable. Please try again later.
1 Author(s)
Asari, V.K. ; Dept. of Electr. & Comput. Eng., Old Dominion Univ., Norfolk, VA, USA

A technique for the training of multiple-valued neural networks based on a backpropagation learning algorithm employing a multilevel threshold function is proposed. The optimum threshold width of the multilevel function and the range of the learning parameter to be chosen for convergence are derived. Trials performed on a benchmark problem demonstrate the convergence of the network within the specified range of parameters

Published in:

Neural Networks, IEEE Transactions on  (Volume:12 ,  Issue: 6 )