A Comparison of Nonlinear Optimisation Strategies for Feed-Forward Adaptive Layered Networks
Abstract
This work discusses various learning strategies which may be employed for the generic class of layered feed-forward adaptive networks exemplified by the traditional Multilayer Perceptron. Such a network is only useful if a set of weight values exists which allows the network to form a good approximation to an underlying (and possibly unknown) transformation between input and output patterns.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jul 05, 1988
- Accession Number
- ADA200044
Entities
People
- A. R. Webb
- David Lowe
- M. D. Bedworth
Organizations
- Royal Signals and Radar Establishment