Neural Networks for Invariant Pattern Recognition


Wood, J. and Shawe-Taylor, J. (1995) Neural Networks for Invariant Pattern Recognition At Proc. of European Symposium on Artificial Neural Networks. , pp. 253-8.

Download

Full text not available from this repository.

Description/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.

Item Type: Conference or Workshop Item (Other)
Additional Information: Organisation: D facto Address: Brussels
Venue - Dates: Proc. of European Symposium on Artificial Neural Networks, 1995-01-01
Organisations: Electronics & Computer Science
ePrint ID: 250473
Date :
Date Event
1995Published
Date Deposited: 01 Jun 1999
Last Modified: 18 Apr 2017 00:20
Further Information:Google Scholar
URI: http://eprints.soton.ac.uk/id/eprint/250473

Actions (login required)

View Item View Item