Output details
11 - Computer Science and Informatics
Aston University
Article title
Computational capabilities of multilayer committee machines
Type
D - Journal article
Title of journal
Journal of physics A: mathematical and theoretical
Article number
445103
Volume number
43
Issue number
44
First page of article
445103
ISSN of journal
1751-8113
Year of publication
2010
Number of additional authors
1
Additional information
<22> This article explored for the first time a special kind of feed-forward neural network: the Ultrametric committee machine. These networks represent the next step in architectural complexity after the perceptron and can be used to separate continuous binary classes with very convoluted boundaries. In particular the paper analysed the measure of difficulty associated to such networks when they act as teachers in an on-line learning scenario. This work is the result of a collaboration with Prof. Leonardo Franco, Universidad de Malaga, Spain.
Interdisciplinary
-
Cross-referral requested
-
Research group
A - Nonlinearity and Complexity Research Group
Citation count
1
Proposed double-weighted
No
Double-weighted statement
-
Reserve for a double-weighted output
No
Non-English
No
English abstract
-