Neural networks for invariant pattern recognition
Neural networks for invariant pattern recognition
In this paper, we discuss a methodology for applying feedforward networks to problems of invariant pattern recognition. We present the Group Representation Network (GRN), a type of feedforward network with the property that its output is invariant under a group of transformations of its input. Since the invariance of such a network is inbuilt, it does not need to be learned. Consequently it is capable of a better generalization performance than a conventional network for solving the same symmetric problem. In addition, the GRN has fewer free parameters than connections and we can hence expect it to train faster than an ordinary network of the same connectivity.
253-258
Wood, J.
65587872-7126-469a-851a-d60195d39058
Shawe-Taylor, John
b1931d97-fdd0-4bc1-89bc-ec01648e928b
1995
Wood, J.
65587872-7126-469a-851a-d60195d39058
Shawe-Taylor, John
b1931d97-fdd0-4bc1-89bc-ec01648e928b
Wood, J. and Shawe-Taylor, John
(1995)
Neural networks for invariant pattern recognition.
In Proceedings of the ESANN'95 Conference, Brussels.
D-Facto Publications.
.
Record type:
Conference or Workshop Item
(Paper)
Abstract
In this paper, we discuss a methodology for applying feedforward networks to problems of invariant pattern recognition. We present the Group Representation Network (GRN), a type of feedforward network with the property that its output is invariant under a group of transformations of its input. Since the invariance of such a network is inbuilt, it does not need to be learned. Consequently it is capable of a better generalization performance than a conventional network for solving the same symmetric problem. In addition, the GRN has fewer free parameters than connections and we can hence expect it to train faster than an ordinary network of the same connectivity.
This record has no associated files available for download.
More information
Published date: 1995
Additional Information:
Organisation: D facto Address: Brussels
Venue - Dates:
European Symposium on Artificial Neural Networks - ESANN 1995, , Brussels, Belgium, 1995-04-19 - 1995-04-21
Organisations:
Electronics & Computer Science
Identifiers
Local EPrints ID: 250473
URI: http://eprints.soton.ac.uk/id/eprint/250473
PURE UUID: b2c15f84-ab5f-4f50-838d-3126dc817865
Catalogue record
Date deposited: 01 Jun 1999
Last modified: 03 Jan 2024 16:07
Export record
Contributors
Author:
J. Wood
Author:
John Shawe-Taylor
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics