Title :
Stochastic backpropagation: a learning algorithm for generalization problems
Author :
Ramamoorthy, C.V. ; Shekhar, Shashi
Author_Institution :
Div. of Comput. Sci., California Univ., Berkeley, CA, USA
Abstract :
Neural networks have traditionally been applied to recognition problems, and most learning algorithms are tailored to those problems. The authors discuss the requirements of learning for generalization, which is NP-complete and cannot be approached by traditional methods based on gradient descent. They present a stochastic learning algorithm based on simulated annealing in weight space. The convergence properties and feasibility of the algorithm are verified
Keywords :
learning systems; neural nets; NP-complete; convergence properties; generalization problems; learning algorithm; neural networks; simulated annealing; stochastic backpropagation; Backpropagation algorithms; Computer science; Convergence; Neural networks; Noise shaping; Shape; Simulated annealing; Speech recognition; Stochastic processes; Testing;
Conference_Titel :
Computer Software and Applications Conference, 1989. COMPSAC 89., Proceedings of the 13th Annual International
Conference_Location :
Orlando, FL
Print_ISBN :
0-8186-1964-3
DOI :
10.1109/CMPSAC.1989.65163
