Sciweavers

2295 search results - page 25 / 459
» Learning Overcomplete Representations
Sort
View
ATAL
2008
Springer
13 years 10 months ago
Transfer of task representation in reinforcement learning using policy-based proto-value functions
Reinforcement Learning research is traditionally devoted to solve single-task problems. Therefore, anytime a new task is faced, learning must be restarted from scratch. Recently, ...
Eliseo Ferrante, Alessandro Lazaric, Marcello Rest...
IJCAI
2007
13 years 10 months ago
Change of Representation for Statistical Relational Learning
Statistical relational learning (SRL) algorithms learn statistical models from relational data, such as that stored in a relational database. We previously introduced view learnin...
Jesse Davis, Irene M. Ong, Jan Struyf, Elizabeth S...
UAIS
2008
155views more  UAIS 2008»
13 years 8 months ago
Adaptive course generation through learning styles representation
This paper presents an approach to automatic course generation and student modeling. The method has been developed during the European funded projects Diogene and Intraserv, focuse...
Enver Sangineto, Nicola Capuano, Matteo Gaeta, Ale...
DCC
2004
IEEE
14 years 8 months ago
Predicting Wavelet Coefficients Over Edges Using Estimates Based on Nonlinear Approximants
It is well-known that wavelet transforms provide sparse decompositions over many types of image regions but not over image singularities/edges that manifest themselves along curve...
Onur G. Guleryuz
ICASSP
2008
IEEE
14 years 3 months ago
Image inpainting with a wavelet domain Hidden Markov tree model
We present a novel technique for image inpainting, the problem of filling-in missing image parts. Image inpainting is ill-posed and we adopt a probabilistic model-based approach ...
George Papandreou, Petros Maragos, Anil Kokaram