Neural Networks for Invariant Pattern Recognition
Wood, J. and Shawe-Taylor, J. (1995) Neural Networks for Invariant Pattern Recognition. Proc. of European Symposium on Artificial Neural Networks , 253-8.
Full text not available from this repository.
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 (UNSPECIFIED)|
|Additional Information:||Organisation: D facto Address: Brussels|
|Divisions:||Faculty of Physical Sciences and Engineering > Electronics and Computer Science
|Date Deposited:||01 Jun 1999|
|Last Modified:||27 Mar 2014 19:51|
|Further Information:||Google Scholar|
|RDF:||RDF+N-Triples, RDF+N3, RDF+XML, Browse.|
Actions (login required)