Title :
Generalization by neural networks
Author :
Shekhar, Shashi ; Amin, Minesh B.
Author_Institution :
Dept. of Comput. Sci., Minnesota Univ., Minneapolis, MN, USA
fDate :
4/1/1992 12:00:00 AM
Abstract :
The authors discuss the requirements of learning for generalization, where the traditional methods based on gradient descent have limited success. A stochastic learning algorithm based on simulated annealing in weight space is presented. The authors verify the convergence properties and feasibility of the algorithm. An implementation of the algorithm and validation experiments are described
Keywords :
learning systems; neural nets; simulated annealing; convergence properties; generalization; gradient descent; learning; neural networks; simulated annealing; stochastic learning algorithm; weight space; Algorithm design and analysis; Annealing; Backpropagation algorithms; Convergence; Curve fitting; Handwriting recognition; Neural networks; Noise shaping; Stochastic processes; Testing;
Journal_Title :
Knowledge and Data Engineering, IEEE Transactions on
