Sciweavers

101 search results - page 7 / 21
» icml 2004
Sort
View
ICML
2004
IEEE
15 years 11 months ago
Learning low dimensional predictive representations
Predictive state representations (PSRs) have recently been proposed as an alternative to partially observable Markov decision processes (POMDPs) for representing the state of a dy...
Matthew Rosencrantz, Geoffrey J. Gordon, Sebastian...
ICML
2004
IEEE
15 years 11 months ago
Decentralized detection and classification using kernel methods
We consider the problem of decentralized detection under constraints on the number of bits that can be transmitted by each sensor. In contrast to most previous work, in which the ...
XuanLong Nguyen, Martin J. Wainwright, Michael I. ...
ICML
2004
IEEE
15 years 11 months ago
Using relative novelty to identify useful temporal abstractions in reinforcement learning
lative Novelty to Identify Useful Temporal Abstractions in Reinforcement Learning ?Ozg?ur S?im?sek ozgur@cs.umass.edu Andrew G. Barto barto@cs.umass.edu Department of Computer Scie...
Özgür Simsek, Andrew G. Barto
ICML
2004
IEEE
15 years 11 months ago
Kernel conditional random fields: representation and clique selection
Kernel conditional random fields (KCRFs) are introduced as a framework for discriminative modeling of graph-structured data. A representer theorem for conditional graphical models...
John D. Lafferty, Xiaojin Zhu, Yan Liu
ICML
2004
IEEE
15 years 11 months ago
A multiplicative up-propagation algorithm
We present a generalization of the nonnegative matrix factorization (NMF), where a multilayer generative network with nonnegative weights is used to approximate the observed nonne...
Jong-Hoon Ahn, Seungjin Choi, Jong-Hoon Oh