12673 search results - page 313 / 2535 » Learning while designing |
179
click to vote
JMLR
2006
2006
Learning Sparse Representations by Non-Negative Matrix Factorization and Sequential Cone Programming
15 years 6 months ago
We exploit the biconvex nature of the Euclidean non-negative matrix factorization (NMF) optimization problem to derive optimization schemes based on sequential quadratic and secon...
165
click to vote
PRL
2006
15 years 6 months ago
2006
This paper studies two types of spatial relationships that can be learned from training examples for object recognition. The first one employs deformable relationships between obj...
189
click to vote
JAIR
2002
15 years 6 months ago
2002
Hidden Markov models hmms and partially observable Markov decision processes pomdps provide useful tools for modeling dynamical systems. They are particularly useful for represent...
227
click to vote
IEEEHPCS
2010
15 years 4 months ago
2010
The performance (in term of error rate) of biometric systems can be improved by combining them. Multiple fusion techniques can be applied from classical logical operations to more...
167
click to vote
ACL
2009
15 years 4 months ago
2009
In this paper, we present a reinforcement learning approach for mapping natural language instructions to sequences of executable actions. We assume access to a reward function tha...