2157 search results - page 250 / 432 » Learning Switching Concepts |
158
Voted
CVPR
1997
IEEE
16 years 7 months ago
1997
IEEE
We propose a new machine learning paradigm called Graph Transformer Networks that extends the applicability of gradient-based learning algorithms to systems composed of modules th...
127
click to vote
ICML
2003
IEEE
16 years 6 months ago
2003
IEEE
In Reinforcement Learning (RL) there has been some experimental evidence that the residual gradient algorithm converges slower than the TD(0) algorithm. In this paper, we use the ...
165
click to vote
ICALT
2007
IEEE
15 years 11 months ago
2007
IEEE
In this paper we propose a set of development guidelines for an adaptive authoring environment of adaptive educational hypermedia. This set consists of relevant and necessary funct...
123
click to vote
COLT
2007
Springer
15 years 11 months ago
2007
Springer
When comparing discrete probability distributions, natural measures of similarity are not p distances but rather are informationdivergences such as Kullback-Leibler and Hellinger. ...
165
click to vote
GECCO
2007
Springer
15 years 11 months ago
2007
Springer
Evolutionary algorithms applied in real domain should profit from information about the local fitness function curvature. This paper presents an initial study of an evolutionary...