๐”– Bobbio Scriptorium
โœฆ   LIBER   โœฆ

Rule-extraction by backpropagation of polyhedra

โœ Scribed by F. Maire

Publisher
Elsevier Science
Year
1999
Tongue
English
Weight
450 KB
Volume
12
Category
Article
ISSN
0893-6080

No coin nor oath required. For personal study only.

โœฆ Synopsis

The core problem of rule-extraction from feed-forward networks is an inversion problem. In this article, we solve this inversion problem by backpropagating unions of polyhedra. We obtain as a by-product a new rule-extraction technique for which the fidelity of the extracted rules can be made arbitrarily high.

๐Ÿ“œ SIMILAR VOLUMES

Fuzzy rule extraction by bacterial memet
Fuzzy rule extraction by bacterial memetic algorithms
โœ J. Botzheim; C. Cabrita; L. T. Kรณczy; A. E. Ruano ๐Ÿ“‚ Article ๐Ÿ“… 2009 ๐Ÿ› John Wiley and Sons ๐ŸŒ English โš– 353 KB

In our previous papers, fuzzy model identification methods were discussed. The bacterial evolutionary algorithm for extracting fuzzy rule base from a training set was presented. The Levenberg-Marquardt method was also proposed for determining membership functions in fuzzy systems. The combination of

An analysis of learning control by backp
An analysis of learning control by backpropagation through time
โœ Sybert Stroeve ๐Ÿ“‚ Article ๐Ÿ“… 1998 ๐Ÿ› Elsevier Science ๐ŸŒ English โš– 370 KB

The main objective of this paper is to indicate how the learning process of a neural control system by backpropagation through time (BTT) is influenced by the structure of the control system, the dynamics of the plant and the parameters of the learning process. Since the analysis of a linear system