Sciweavers

508 search results - page 49 / 102
» A Variational Approach to Learning Curves
Sort
View
ICDE
2000
IEEE
189views Database» more  ICDE 2000»
16 years 2 months ago
Image Database Retrieval with Multiple-Instance Learning Techniques
In this paper, we develop and test an approach to retrieving images from an image database based on content similarity. First, each picture is divided into many overlapping region...
Cheng Yang, Tomás Lozano-Pérez
AIME
2003
Springer
15 years 6 months ago
Learning-Free Text Categorization
In this paper, we report on the fusion of simple retrieval strategies with thesaural resources in order to perform large-scale text categorization tasks. Unlike most related system...
Patrick Ruch, Robert H. Baud, Antoine Geissbü...
NIPS
2001
15 years 2 months ago
Variance Reduction Techniques for Gradient Estimates in Reinforcement Learning
Policy gradient methods for reinforcement learning avoid some of the undesirable properties of the value function approaches, such as policy degradation (Baxter and Bartlett, 2001...
Evan Greensmith, Peter L. Bartlett, Jonathan Baxte...
COLING
1992
15 years 2 months ago
Syntactic Ambiguity Resolution Using A Discrimination and Robustness Oriented Adaptive Learning Algorithm
In this paper, a discrimination and robusmess oriented adaptive learning procedure is proposed to deal with the task of syntactic ambiguity resolution. Owing to the problem of ins...
Tung-Hui Chiang, Yi-Chung Lin, Keh-Yih Su
ICASSP
2011
IEEE
14 years 5 months ago
Maximum marginal likelihood estimation for nonnegative dictionary learning
We describe an alternative to standard nonnegative matrix factorisation (NMF) for nonnegative dictionary learning. NMF with the Kullback-Leibler divergence can be seen as maximisa...
Onur Dikmen, Cédric Févotte