mk:icec97
Summary
A Neural Network that uses Evolutionary Learning. Mario Köppen, Martin Teunis and Bertram Nickolay. In Proceedings ICEC'97, Indianapolis, IN, pages 635-639, 1997.
Abstract
This paper proposes a new neural architecture (Nessy) which uses evolutionary optimization for learning. The architecture, the outline of its evolutionary algorithm and the learning laws are given. Nessy is based on sev- eral modi cations of the multilayer backpropagation neural network. The neurons represent genes of evolutionary opti- mization, refered to as solutions. Weights represent proba- bilities and are used for selectioning. The training value of the output layer is set to Zero, the theoretical limit of ev- ery cost-oriented optimization, and the crossover operator is replaced by a transduction operator. Mutation is used as usual. Nessy algorithm can be characterized as individual evolutionary algorithm, but as a neural network too. It was designed for image processing applications. A short example is presented, where the discriminative feature of two images is succesfully detected by the proposed evolutionary neural network.
Bibtex entry
@INPROCEEDINGS { mk:icec97,
ABSTRACT = { This paper proposes a new neural architecture (Nessy) which uses evolutionary optimization for learning. The architecture, the outline of its evolutionary algorithm and the learning laws are given. Nessy is based on sev- eral modi cations of the multilayer backpropagation neural network. The neurons represent genes of evolutionary opti- mization, refered to as solutions. Weights represent proba- bilities and are used for selectioning. The training value of the output layer is set to Zero, the theoretical limit of ev- ery cost-oriented optimization, and the crossover operator is replaced by a transduction operator. Mutation is used as usual. Nessy algorithm can be characterized as individual evolutionary algorithm, but as a neural network too. It was designed for image processing applications. A short example is presented, where the discriminative feature of two images is succesfully detected by the proposed evolutionary neural network. },
AUTHOR = { Mario Köppen and Martin Teunis and Bertram Nickolay },
BOOKTITLE = { Proceedings ICEC'97, Indianapolis, IN },
MODIFIED = { 2008-02-28 17:01:49 +0900 },
HASABSTRACT = { Yes },
PAGES = { 635--639 },
PDF = { icec97.pdf },
TITLE = { A Neural Network that uses Evolutionary Learning },
YEAR = { 1997 },
}