2103 search results - page 92 / 421 » Approximate Learning of Dynamic Models |
132
click to vote
NN
2008
Springer
15 years 4 months ago
2008
Springer
Currently, there is a lack of general-purpose in-place learning networks that model feature layers in the cortex. By "general-purpose" we mean a general yet adaptive hig...
130
click to vote
ICML
2007
IEEE
16 years 5 months ago
2007
IEEE
We propose a class of graphical models appropriate for structure prediction problems where the model structure is a function of the output structure. Incremental Sigmoid Belief Ne...
125
click to vote
NECO
2002
15 years 4 months ago
2002
We propose a modular reinforcement learning architecture for non-linear, nonstationary control tasks, which we call multiple model-based reinforcement learning (MMRL). The basic i...
146
click to vote
ECML
2007
Springer
15 years 11 months ago
2007
Springer
We present a framework for efficient, accurate approximate Bayesian inference in generalized linear models (GLMs), based on the expectation propagation (EP) technique. The paramete...
159
click to vote
IJCNN
2007
IEEE
15 years 11 months ago
2007
IEEE
— In this paper we provide experimental results and extensions to our previous theoretical findings concerning the combination of forecasts that have been diversified by three ...