Output details
13 - Electrical and Electronic Engineering, Metallurgy and Materials
Queen's University Belfast
Article title
A new Jacobian matrix for optimal learning of single-layer neural networks
Type
D - Journal article
Title of journal
IEEE Transactions on Neural Networks
Article number
-
Volume number
19
Issue number
1
First page of article
119
ISSN of journal
1045-9227
Year of publication
2008
URL
-
Number of additional authors
2
Additional information
This EPSRC (GR/S85191/01) funded research introduces for the first time a new Jacobian matrix which yields a more accurate approximation of the true cost function for the training of single-layer forward neural networks (SLFNs) using second-order learning algorithms. This enables the development of a novel analytic framework which helps to speed up the convergence of network learning and to improve the network generalization performance, confirmed by its application to benchmark problems. This research resulted in a number of invited research seminars given in leading Chinese universities through a RCUK funded UK-China Science Bridge project (EP/G042594/1).
Interdisciplinary
-
Cross-referral requested
-
Research group
C - Energy, Power and Intelligent Control (EPIC)
Proposed double-weighted
No
Double-weighted statement
-
Reserve for a double-weighted output
No
Non-English
No
English abstract
-
