4255 search results - page 550 / 851 » On Learning Boolean Functions |
165
click to vote
NIPS
2007
15 years 8 months ago
2007
We present a novel linear clustering framework (DIFFRAC) which relies on a linear discriminative cost function and a convex relaxation of a combinatorial optimization problem. The...
166
click to vote
UAI
2008
15 years 8 months ago
2008
We introduce a new type of graphical model called a `cumulative distribution network' (CDN), which expresses a joint cumulative distribution as a product of local functions. ...
160
click to vote
NIPS
2003
15 years 8 months ago
2003
Recent developments in grid-based and point-based approximation algorithms for POMDPs have greatly improved the tractability of POMDP planning. These approaches operate on sets of...
145
click to vote
CORR
2006
Springer
15 years 6 months ago
2006
Springer
Competitive on-line prediction (also known as universal prediction of individual sequences) is a strand of learning theory avoiding making any stochastic assumptions about the way...
176
click to vote
IJON
2008
15 years 6 months ago
2008
Identifiability becomes an essential requirement for learning machines when the models contain physically interpretable parameters. This paper presents two approaches to examining...