๐”– Bobbio Scriptorium
โœฆ   LIBER   โœฆ

On the relations between discriminant analysis and multilayer perceptrons

โœ Scribed by P. Gallinari; S. Thiria; F. Badran; F. Fogelman-Soulie

Publisher
Elsevier Science
Year
1991
Tongue
English
Weight
966 KB
Volume
4
Category
Article
ISSN
0893-6080

No coin nor oath required. For personal study only.

โœฆ Synopsis

We study the relations between discriminant analysis" and multilayer perceptrons used fi~r classification tasks. We first consider linear networks and prove the formal equivalence between the two techniques in this case. We then present a set of experiments on problems with increasing degree of nonlinearity. This allows to study the extension of this result to nonlinear nets and to investigate data transformations in the suceessive layers o[ these nets. Finally, we show evidence o( generic properties of MLPs classifiers.

๐Ÿ“œ SIMILAR VOLUMES

Comparison of multilayer perceptron and
Comparison of multilayer perceptron and probabilistic neural networks in artificial vision. Application to the discrimination of seeds
โœ Younes Chtioui; Dominique Bertrand; Marie-Francoise Devaux; Dominique Barba ๐Ÿ“‚ Article ๐Ÿ“… 1997 ๐Ÿ› John Wiley and Sons ๐ŸŒ English โš– 387 KB ๐Ÿ‘ 2 views

In classification problems the most commonly used neural network is probably the multilayer perceptron network (MLPN). The probabilistic neural network (PNN) is a possible alternative to the MLPN. The PNN is based on the Bayesian approach and a non-parametric estimation of the probability density fu

On the relations between continuous and
On the relations between continuous and nonatomic measures
โœ Wolfgang Adamski ๐Ÿ“‚ Article ๐Ÿ“… 1980 ๐Ÿ› John Wiley and Sons ๐ŸŒ English โš– 338 KB

## On the relations between continuous and nonatomic measures By WOLFGANG ADAMSKI of Munchen (Eingegangen am 21. 5. 1979) It is the purpose of this paper to study the relations between continuous and nonatomic (finite, nonnegative, countably additive) measures, where a measure defined on a o-alge