Two papers on feed-forward networks
- Author
- Buntine, Wray L.
- Published
- Jul 5, 1991.
- Physical Description
- 1 electronic document
- Additional Creators
- Weigend, Andreas S.
Online Version
- hdl.handle.net , Connect to this object online.
- Restrictions on Access
- Unclassified, Unlimited, Publicly available.
Free-to-read Unrestricted online access - Summary
- Connectionist feed-forward networks, trained with back-propagation, can be used both for nonlinear regression and for (discrete one-of-C) classification, depending on the form of training. This report contains two papers on feed-forward networks. The papers can be read independently. They are intended for the theoretically-aware practitioner or algorithm-designer; however, they also contain a review and comparison of several learning theories so they provide a perspective for the theoretician. The first paper works through Bayesian methods to complement back-propagation in the training of feed-forward networks. The second paper addresses a problem raised by the first: how to efficiently calculate second derivatives on feed-forward networks.
- Other Subject(s)
- Collection
- NASA Technical Reports Server (NTRS) Collection.
- Note
- Document ID: 19920017388.
Accession ID: 92N26631.
NAS 1.15:107840.
NASA-TM-107840.
FIA-91-22. - Terms of Use and Reproduction
- No Copyright.
View MARC record | catkey: 15675320