Referenced Items are not available for this document.
The general formula of computing the deviation of the output of a multilayer neural network (MLNN) with respect to the deviations of its input and of its weights is presented. The upper bound of the deviation propagation from level to level is well estimated with certain probability. Based on this, one can analyze the relation between the topological structure of an MLNN and its fault tolerance property, which can be used to correctly design fault tolerant MLNNs
Published in:
Neural Networks, 1993., IEEE International Conference on
Date of Conference: 1993
- Page(s):
- 1034 - 1039 vol.2
- Meeting Date :
- 28 Mar 1993-01 Apr 1993
- Print ISBN:
- 0-7803-0999-5
- INSPEC Accession Number:
- 4720665
- Conference Location :
- San Francisco, CA
- Digital Object Identifier :
- 10.1109/ICNN.1993.298700
- Product Type:
- Conference Publications
About IEEE Xplore | Contact | Help | Terms of Use | Nondiscrimination Policy | Site Map | Privacy & Opting Out of Cookies
A not-for-profit organization, IEEE is the world's largest professional association for the advancement of technology.
© Copyright 2013 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.
