2711 search results - page 490 / 543 » Convergence of the Wake-Sleep Algorithm |
AAAI
2008
15 years 4 days ago
2008
Hierarchical state decompositions address the curse-ofdimensionality in Q-learning methods for reinforcement learning (RL) but can suffer from suboptimality. In addressing this, w...
CEC
2007
IEEE
14 years 11 months ago
2007
IEEE
Abstract—The high-level synthesis process allows the automatic design and implementation of digital circuits starting from a behavioral description. Evolutionary algorithms are v...
ESA
2008
Springer
14 years 11 months ago
2008
Springer
The focus is on black-box optimization of a function f : RN R given as a black box, i. e. an oracle for f-evaluations. This is commonly called direct search, and in fact, most meth...
NIPS
2008
14 years 11 months ago
2008
This work characterizes the generalization ability of algorithms whose predictions are linear in the input vector. To this end, we provide sharp bounds for Rademacher and Gaussian...
NIPS
2008
14 years 11 months ago
2008
Bartlett et al (2006) recently proved that a ground condition for convex surrogates, classification calibration, ties up the minimization of the surrogates and classification risk...