O. Ekeberg and A. Lansner, "Automatic generation of internal representations in a probabilistic artificial neural network," Proceedings of the First European Conference on Neural Networks, June 6-9 1988. Home/Search Document Not in Database Summary Related Articles |
This paper is cited in the following contexts:
Classification and Approximation with Rule-Based Networks - Higgins, Jr. (Correct)
....more complex relationships. Somewhere between these two extremes lie systems which decide which higher order conjunctive probabilities to store without storing them all. Networks which choose such higher order connections randomly were among the first neural networks [Ros62] Ekeberg and Lansner [EL88] show a method based on a correlation dependency measure for deciding which such probabilities to store, but again must assume independence of attributes to estimate conditional probabilities. We will show in this thesis that information theory provides a measure for deciding which higher order ....
O. Ekeberg and A. Lansner, "Automatic generation of internal representations in a probabilistic artificial neural network," Proceedings of the First European Conference on Neural Networks, June 6-9 1988.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC