Paper on Neuroprose

[John Shawe-Taylor]

The following paper has recently been accepted to appear in 
IEEE Transactions on Neural Networks and has been placed in the
Neuroprose archive as shawetaylor.symdisc.ps.Z.

-----------------------------
Symmetries and Discriminability in Feedforward Network
                   Architectures
  John Shawe-Taylor, Department of Computer Science,
        Royal Holloway, University of London

Abstract: The 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 transformations 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 of which inputs
can be distinguished by such architectures.    A theorem 
characterising 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 non-isomorphic graphs if and 
only if the graph reconstruction conjecture holds.


To retrieve the file:

unix> ftp cheops.cis.ohio-state.edu
Connected to cheops.cis.ohio-state.edu.
220 cheops.cis.ohio-state.edu FTP server ready.
Name: anonymous
331 Guest login ok, send ident as password.
Password:neuron
230 Guest login ok, access restrictions apply.
ftp> binary
200 Type set to I.
ftp> cd pub/neuroprose
250 CWD command successful.
ftp> get shawetaylor.symdisc.ps.Z
200 PORT command successful.
150 Opening BINARY mode data connection for shawetaylor.symdisc.ps.Z
226 Transfer complete.
100000 bytes sent in 3.14159 seconds
ftp> quit
221 Goodbye.
unix> uncompress shawetaylor.symdisc.ps.Z
unix> lpr shawetaylor.symdisc.ps (or however you print out postscript)