Generalization by Neural Networks

Shashi Shekhar, Minesh B. Amin

Research output: Contribution to journalArticlepeer-review

14 Scopus citations


Neural networks have traditionally been applied to recognition problems, and most learning algorithms are tailored to those problems. We discuss the requirements of learning for generalization, where the traditional methods based on gradient descent have limited success. We present a new stochastic learning algorithm based on simulated annealing in weight space. We verify the convergence properties and feasibility of the algorithm. We also describe an implementation of the algorithm and validation experiments.

Original languageEnglish (US)
Pages (from-to)177-185
Number of pages9
JournalIEEE Transactions on Knowledge and Data Engineering
Issue number2
StatePublished - Apr 1992


Dive into the research topics of 'Generalization by Neural Networks'. Together they form a unique fingerprint.

Cite this