Sciweavers

869 search results - page 30 / 174
» An Effective Learning Method for Max-Min Neural Networks
Sort
View
ICANN
2010
Springer
13 years 9 months ago
Empirical Analysis of the Divergence of Gibbs Sampling Based Learning Algorithms for Restricted Boltzmann Machines
Abstract. Learning algorithms relying on Gibbs sampling based stochastic approximations of the log-likelihood gradient have become a common way to train Restricted Boltzmann Machin...
Asja Fischer, Christian Igel
ICMCS
2007
IEEE
145views Multimedia» more  ICMCS 2007»
14 years 2 months ago
MUSEMBLE: A Music Retrieval System Based on Learning Environment
Query reformulation has been suggested as an effective way to improve retrieval efficiency in text information retrieval and one of the well-known techniques for query reformulati...
Seungmin Rho, Byeong-jun Han, Eenjun Hwang, Minkoo...
ICMLA
2010
13 years 6 months ago
Ensembles of Neural Networks for Robust Reinforcement Learning
Reinforcement learning algorithms that employ neural networks as function approximators have proven to be powerful tools for solving optimal control problems. However, their traini...
Alexander Hans, Steffen Udluft
WCE
2007
13 years 9 months ago
Neural Networks for Optimal Control of Aircraft Landing Systems
Abstract—In this work we present a variational formulation for a multilayer perceptron neural network. With this formulation any learning task for the neural network is defined ...
Kevin Lau, Roberto Lopez, Eugenio Oñate
TR
2010
149views Hardware» more  TR 2010»
13 years 3 months ago
Health Condition Prediction of Gears Using a Recurrent Neural Network Approach
Abstract--The development of accurate health condition prediction approaches has been a key research topic in condition based maintenance (CBM) in recent years. However, current he...
Zhigang Tian, Ming J. Zuo