Estimating hidden unit number for two-layer perceptrons
- 1 January 1989
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 677-681 vol.1
- https://doi.org/10.1109/ijcnn.1989.118651
Abstract
A method of estimating the number of hidden units required by a two-layer perceptron learning binary mappings using back propagation of error signals is presented. In order to obtain an estimate of the number of hidden units for a fully connected net with n output units, it is necessary to obtain an estimate of the number of 'conflicts' contained in the individual binary responses that must be learned by each output unit. A conflict is a set of input/output relationships that require incompatible weight solutions when the responses of an output unit are learned on a single layer perceptron. The estimate produced is data-dependent, since the number of conflicts for an output unit depends on the specific responses of the output unit to the input vectors contained in the training set.Keywords
This publication has 6 references indexed in Scilit:
- A pipelined associated memory implemented in VLSIIEEE Journal of Solid-State Circuits, 1989
- On the capabilities of multilayer perceptronsJournal of Complexity, 1988
- An algebraic projection analysis for optimal hidden units size and learning rates in back-propagation learningPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1988
- HIERtalker: a default hierarchy of high order neural networks that learns to read English aloudPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1988
- Parallel Distributed ProcessingPublished by MIT Press ,1986
- Synchronous and asynchronous systems of threshold elementsBiological Cybernetics, 1983