Format

Send to

Choose Destination
Neural Netw. 1997 Mar;10(2):343-352.

The New ERA in Supervised Learning.

Author information

1
King's College, London, UK

Abstract

Conventional methods of supervised learning are inevitably faced with the problem of local minima; evidence is presented that second order methods such as the conjugate gradient and quasi-Newton techniques are particularly susceptible to being trapped in sub-optimal solutions. A new technique, expanded range approximation (ERA), is presented, which by the use of a homotopy on the range of the target outputs allows supervised learning methods to find a global minimum of the error function in almost every case.

PMID:
12662532

Supplemental Content

Full text links

Icon for Elsevier Science
Loading ...
Support Center