Building Symmetries into Feedforward Networks
ShaweTaylor, John (1989) Building Symmetries into Feedforward Networks In Proceedings of First IEE Conference on Artificial Neural Networks, London. Inspec/Iee., pp. 158162.
Download
Full text not available from this repository.
Description/Abstract
One of the central tools developed by M. Minsky and S. Papert (1988) was the group invariance theorem. This theorem is concerned with choosing perceptron weights to recognise a predicate that is invariant under a group of permutations of the input. The theorem states that the weights can be chosen to be constant for equivalence classes of predicates under the action of the group. This paper presents this result in a graph theoretic light and then extends consideration to multilayer perceptrons. It is shown that, by choosing a multilayer network in such a way that the action of the group on the input nodes can be extended to the whole network, the invariance of the output under the action of the group can be guaranteed. This greatly reduces the number of degrees of freedom in the training of such a network. An example of using this technique to train a network to recognise isomorphism classes of graphs is given. This compares favourably with previous experiments using standard backpropagation. The connections between the group of symmetries and the network structure are explored and the relation to the problem of graph isomorphism is discussed
Item Type:  Conference or Workshop Item (Paper)  

ISBNs:  0852963882 (print) 

Organisations:  Electronics & Computer Science  
ePrint ID:  259738  
Date : 


Date Deposited:  12 Aug 2004  
Last Modified:  17 Apr 2017 22:24  
Further Information:  Google Scholar  
URI:  http://eprints.soton.ac.uk/id/eprint/259738 
Actions (login required)
View Item 