2436 search results - page 175 / 488 » Evaluating Adaptive Problem Selection |
160
Voted
ICML
2000
IEEE
16 years 4 months ago
2000
IEEE
Eligibility traces have been shown to speed reinforcement learning, to make it more robust to hidden states, and to provide a link between Monte Carlo and temporal-difference meth...
131
Voted
TSMC
2011
14 years 10 months ago
2011
—This paper introduces an algorithm for direct search of control policies in continuous-state discrete-action Markov decision processes. The algorithm looks for the best closed-l...
152
Voted
KDD
2009
ACM
16 years 4 months ago
2009
ACM
When labeled examples are limited and difficult to obtain, transfer learning employs knowledge from a source domain to improve learning accuracy in the target domain. However, the...
116
Voted
HICSS
2002
IEEE
15 years 8 months ago
2002
IEEE
With the increasing availability of Web-enabled mobile devices, we are facing the problem to effectively adapt Web content for those devices. For adaptation, Web page structures r...
141
click to vote
PRL
2010
15 years 2 months ago
2010
The strength of gait, compared to other biometrics, is that it does not require cooperative subjects. Previoius gait recognition approaches were evaluated using a gallery set cons...