A Sum Rule Satisfied by Optimised Feed-Forward Layered Networks
Abstract
Take a feed-forward layered network (such as a multilayer perceptron or a radial basis function network) which is to operate as a pattern classifier. The network may have several hidden layers, as many nodes as required and any desired nonlinearities on the hidden units. The transfer functions of the output nodes should be linear. If the network is trained (using any appropriate problem) to minimise the sum squared error over all outputs and patterns such that the output weights have minimum norm, then the output values of the trained network for any subsequent input pattern will sum to a constant. keywords: Radar, Great Britain.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 24, 1989
- Accession Number
- ADA220767
Entities
People
- A. R. Webb
- D. Lowe
- D. S. Broomhead
Organizations
- Royal Signals and Radar Establishment