A functional analytic approach to incremental learning in optimally generalizing neural networks

S. Vijayakumar, H. Ogawa

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

For a given set of training data, a method of learning for optimally generalizing neural networks using functional analytic approach already exists. Here, we consider the case when additional training data is made available at a later stage. We devise a method of carrying out optimal learning with respect to the entire set of training data (including the newly added one) using the results of the previously learned stage. This ensures that the learning operator and the learned function can both be computed incrementally, leading to a reduced computational cost. Finally, we also provide a simplified relationship between the newly learned function and the previous function, opening avenues for work into selection of optimal training set.
Original languageEnglish
Title of host publicationNeural Networks, 1995. Proceedings., IEEE International Conference on
Pages777-782
Number of pages6
Volume2
DOIs
Publication statusPublished - 1995

Fingerprint

Dive into the research topics of 'A functional analytic approach to incremental learning in optimally generalizing neural networks'. Together they form a unique fingerprint.

Cite this