Sciweavers

215 search results - page 11 / 43
» Mathematical Aspects of Neural Networks
Sort
View
TNN
2008
88views more  TNN 2008»
13 years 6 months ago
A New Approach to Knowledge-Based Design of Recurrent Neural Networks
Abstract-- A major drawback of artificial neural networks (ANNs) is their black-box character. This is especially true for recurrent neural networks (RNNs) because of their intrica...
Eyal Kolman, Michael Margaliot
GECCO
2008
Springer
261views Optimization» more  GECCO 2008»
13 years 7 months ago
SSNNS -: a suite of tools to explore spiking neural networks
We are interested in engineering smart machines that enable backtracking of emergent behaviors. Our SSNNS simulator consists of hand-picked tools to explore spiking neural network...
Heike Sichtig, J. David Schaffer, Craig B. Laramee
GECCO
2008
Springer
196views Optimization» more  GECCO 2008»
13 years 7 months ago
ADANN: automatic design of artificial neural networks
In this work an improvement of an initial approach to design Artificial Neural Networks to forecast Time Series is tackled, and the automatic process to design Artificial Neural N...
Juan Peralta, Germán Gutiérrez, Arac...
ISNN
2010
Springer
13 years 11 months ago
Learning to Believe by Feeling: An Agent Model for an Emergent Effect of Feelings on Beliefs
An agent's beliefs usually depend on cognitive factors, but also affective factors may play a role. This paper presents an agent model that shows how such affective effects on...
Zulfiqar A. Memon, Jan Treur
IWANN
2001
Springer
13 years 11 months ago
Pattern Repulsion Revisited
Marques and Almeida [9] recently proposed a nonlinear data seperation technique based on the maximum entropy principle of Bell and Sejnowsky. The idea behind is a pattern repulsion...
Fabian J. Theis, Christoph Bauer, Carlos Garc&iacu...