Recurrence methods in the analysis of learning processes

S. Mendelson*, I. Nelken

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

The goal of most learning processes is to bring a machine into a set of "correct" states. In practice, however, it may be difficult to show that the process enters this target set. We present a condition that ensures that the process visits the target set infinitely often almost surely. This condition is easy to verify and is true for many well-known learning rules. To demonstrate the utility of this method, we apply it to four types of learning processes: the perceptron, learning rules governed by continuous energy functions, the Kohonen rule, and the committee machine.

Original languageAmerican English
Pages (from-to)1839-1861
Number of pages23
JournalNeural Computation
Volume13
Issue number8
DOIs
StatePublished - Aug 2001

Fingerprint

Dive into the research topics of 'Recurrence methods in the analysis of learning processes'. Together they form a unique fingerprint.

Cite this