Sciweavers

932 search results - page 81 / 187
» Referring-Expression Generation Using a Transformation-Based...
Sort
View
115
Voted
CORR
2002
Springer
95views Education» more  CORR 2002»
15 years 2 months ago
Unsupervised Learning of Morphology without Morphemes
The first morphological learner based upon the theory of Whole Word Morphology (Ford et al., 1997) is outlined, and preliminary evaluation results are presented. The program, Whol...
Sylvain Neuvel, Sean A. Fulop
123
Voted
ICANN
2010
Springer
15 years 3 months ago
Exploring Continuous Action Spaces with Diffusion Trees for Reinforcement Learning
We propose a new approach for reinforcement learning in problems with continuous actions. Actions are sampled by means of a diffusion tree, which generates samples in the continuou...
Christian Vollmer, Erik Schaffernicht, Horst-Micha...
149
Voted
ICPR
2010
IEEE
15 years 13 days ago
Multiple Kernel Learning with High Order Kernels
Previous Multiple Kernel Learning approaches (MKL) employ different kernels by their linear combination. Though some improvements have been achieved over methods using single kerne...
Shuhui Wang, Shuqiang Jiang, Qingming Huang, Qi Ti...
ICCV
2009
IEEE
1824views Computer Vision» more  ICCV 2009»
16 years 7 months ago
Beyond the Euclidean distance: Creating effective visual codebooks using the histogram intersection kernel
Common visual codebook generation methods used in a Bag of Visual words model, e.g. k-means or Gaussian Mixture Model, use the Euclidean distance to cluster features into visual...
Jianxin Wu, James M. Rehg
GECCO
2010
Springer
184views Optimization» more  GECCO 2010»
15 years 7 months ago
Transfer learning through indirect encoding
An important goal for the generative and developmental systems (GDS) community is to show that GDS approaches can compete with more mainstream approaches in machine learning (ML)....
Phillip Verbancsics, Kenneth O. Stanley