Sciweavers

945 search results - page 179 / 189
» Dialog Convergence and Learning
Sort
View
CDC
2010
IEEE
136views Control Systems» more  CDC 2010»
13 years 4 months ago
Pathologies of temporal difference methods in approximate dynamic programming
Approximate policy iteration methods based on temporal differences are popular in practice, and have been tested extensively, dating to the early nineties, but the associated conve...
Dimitri P. Bertsekas
JAIR
2011
187views more  JAIR 2011»
13 years 4 months ago
A Monte-Carlo AIXI Approximation
This paper describes a computationally feasible approximation to the AIXI agent, a universal reinforcement learning agent for arbitrary environments. AIXI is scaled down in two ke...
Joel Veness, Kee Siong Ng, Marcus Hutter, William ...
JMLR
2010
191views more  JMLR 2010»
13 years 4 months ago
Noise-contrastive estimation: A new estimation principle for unnormalized statistical models
We present a new estimation principle for parameterized statistical models. The idea is to perform nonlinear logistic regression to discriminate between the observed data and some...
Michael Gutmann, Aapo Hyvärinen
TKDE
2010
224views more  TKDE 2010»
13 years 4 months ago
Non-Negative Matrix Factorization for Semisupervised Heterogeneous Data Coclustering
Coclustering heterogeneous data has attracted extensive attention recently due to its high impact on various important applications, such us text mining, image retrieval, and bioin...
Yanhua Chen, Lijun Wang, Ming Dong
CORR
2011
Springer
177views Education» more  CORR 2011»
13 years 1 months ago
Gossip PCA
Eigenvectors of data matrices play an important role in many computational problems, ranging from signal processing to machine learning and control. For instance, algorithms that ...
Satish Babu Korada, Andrea Montanari, Sewoong Oh