Title :
Training of a feedforward multiple-valued neural network by error backpropagation with a multilevel threshold function
Author :
Asari, Vijayan K.
Author_Institution :
Dept. of Electr. & Comput. Eng., Old Dominion Univ., Norfolk, VA, USA
fDate :
11/1/2001 12:00:00 AM
Abstract :
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
Keywords :
backpropagation; convergence; feedforward neural nets; multilayer perceptrons; backpropagation learning algorithm; convergence; error backpropagation; feedforward multiple-valued neural network; learning parameter; multilevel threshold function; Artificial neural networks; Backpropagation algorithms; Biological system modeling; Convergence; Feedforward neural networks; Logic; Multi-layer neural network; Neural networks; Neurons; Pattern recognition;
Journal_Title :
Neural Networks, IEEE Transactions on
