Symmetries and Discriminability in Feedforward Network Architectures

Shawe-Taylor, J. (1993) Symmetries and Discriminability in Feedforward Network Architectures. IEEE Transactions on Neural Networks, 4, (5), 816-826.


[img] PDF
Download (1027Kb)


This paper investigates the effects of introducing symmetries into feedforward neural networks in what are termed symmetry networks. This technique allows more efficient training for problems in which we require the output of a network to be invariant under a set of tranformations of the input. The particular problem of graph recognition is considered. In this case the network is designed to deliver the same output for isomorphic graphs. This leads to the question fo which inputs can be distinguished by such artitectures. A theorem characterizing when two inputs can be distinguished by a symmetry network is given. As a consequence, a particular network design is shown to be able to distinguish nonisomorphic graphs if and only if the graph reconstruction conjecture holds.

Item Type: Article
ISSNs: 1045-9227
Related URLs:
Divisions : Faculty of Physical Sciences and Engineering > Electronics and Computer Science
ePrint ID: 259819
Accepted Date and Publication Date:
September 1993Published
Date Deposited: 03 Sep 2004
Last Modified: 31 Mar 2016 14:01
Further Information:Google Scholar

Actions (login required)

View Item View Item

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