Year: 2001
Type: conference-paper
Abstract: The storage capacity of an incremental learning algorithm for the parity machine, the Tilinglike Learning Algorithm, is analytically determined in the limit of a large number of hidden perceptrons. Different learning rules for the simple perceptron are investigated. The usual Gardner-Derrida rule leads to a storage capacity close to the upper bound, which is independent of the learning algorithm considered.
Source: AIP conference proceedings
DOI: 10.1063/1.1358157
Author: Arnaud Buhot
Institution: University of Oxford
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W1595360233