Neural Computation, Vol 8, 869-893, Copyright © 1996 by The MIT Press
Engineering multiversion neural-net systems
D Partridge and WB Yates
Department of Computer Science, University of Exeter, England.
In this paper we address the problem of constructing reliable neural- net
implementations, given the assumption that any particular implementation
will not be totally correct. The approach taken in this paper is to
organize the inevitable errors so as to minimize their impact in the
context of a multiversion system, i.e., the system functionality is
reproduced in multiple versions, which together will constitute the
neural-net system. The unique characteristics of neural computing are
exploited in order to engineer reliable systems in the form of diverse,
multiversion systems that are used together with a "decision strategy"
(such as majority vote). Theoretical notions of "methodological diversity"
contributing to the improvement of system performance are implemented and
tested. An important aspect of the engineering of an optimal system is to
overproduce the components and then choose an optimal subset. Three general
techniques for choosing final system components are implemented and
evaluated. Several different approaches to the effective engineering of
complex multiversion systems designs are realized and evaluated to
determine overall reliability as well as reliability of the overall system
in comparison to the lesser reliability of component substructures.
