Sciweavers

4096 search results - page 262 / 820
» Fibring Neural Networks
Sort
View
ECAI
2010
Springer
15 years 7 months ago
Unsupervised Layer-Wise Model Selection in Deep Neural Networks
Abstract. Deep Neural Networks (DNN) propose a new and efficient ML architecture based on the layer-wise building of several representation layers. A critical issue for DNNs remain...
Ludovic Arnold, Hélène Paugam-Moisy,...
GECCO
2008
Springer
179views Optimization» more  GECCO 2008»
15 years 7 months ago
A hybrid method for tuning neural network for time series forecasting
This paper presents an study about a new Hybrid method GRASPES - for time series prediction, inspired in F. Takens theorem and based on a multi-start metaheuristic for combinatori...
Aranildo Rodrigues Lima Junior, Tiago Alessandro E...
ASC
2007
15 years 6 months ago
Evolving an artificial neural network classifier for condition monitoring of rotating mechanical systems
We present the results of our investigation into the use of Genetic Algorithms (GAs) for identifying near optimal design parameters of diagnostic systems that are based on Artifici...
Abhinav Saxena, Ashraf Saad
ESWA
2006
154views more  ESWA 2006»
15 years 6 months ago
Artificial neural networks with evolutionary instance selection for financial forecasting
In this paper, I propose a genetic algorithm (GA) approach to instance selection in artificial neural networks (ANNs) for financial data mining. ANN has preeminent learning abilit...
Kyoung-jae Kim
TNN
2008
138views more  TNN 2008»
15 years 6 months ago
A Fast and Scalable Recurrent Neural Network Based on Stochastic Meta Descent
This brief presents an efficient and scalable online learning algorithm for recurrent neural networks (RNNs). The approach is based on the real-time recurrent learning (RTRL) algor...
Zhenzhen Liu, Itamar Elhanany