Sciweavers

22 search results - page 2 / 5
» A New Continuous Action-Set Learning Automaton for Function ...
Sort
View
NN
2000
Springer
192views Neural Networks» more  NN 2000»
13 years 4 months ago
A new algorithm for learning in piecewise-linear neural networks
Piecewise-linear (PWL) neural networks are widely known for their amenability to digital implementation. This paper presents a new algorithm for learning in PWL networks consistin...
Emad Gad, Amir F. Atiya, Samir I. Shaheen, Ayman E...
ICPR
2008
IEEE
13 years 11 months ago
Optimal feature weighting for the continuous HMM
We propose new Continuous Hidden Markov Model (CHMM) structure that integrates feature weighting component. We assume that each feature vector could include different subsets of f...
Oualid Missaoui, Hichem Frigui
AAAI
2006
13 years 6 months ago
Learning Basis Functions in Hybrid Domains
Markov decision processes (MDPs) with discrete and continuous state and action components can be solved efficiently by hybrid approximate linear programming (HALP). The main idea ...
Branislav Kveton, Milos Hauskrecht
CEC
2005
IEEE
13 years 10 months ago
XCS with computed prediction for the learning of Boolean functions
Computed prediction represents a major shift in learning classifier system research. XCS with computed prediction, based on linear approximators, has been applied so far to functi...
Pier Luca Lanzi, Daniele Loiacono, Stewart W. Wils...
ABIALS
2008
Springer
13 years 7 months ago
Multiscale Anticipatory Behavior by Hierarchical Reinforcement Learning
Abstract. In order to establish autonomous behavior for technical systems, the well known trade-off between reactive control and deliberative planning has to be considered. Within ...
Matthias Rungger, Hao Ding, Olaf Stursberg