876 search results - page 46 / 176 » On a theory of learning with similarity functions |
IGPL
2008
14 years 11 months ago
2008
We propose here an extension of Rice's Theorem to first-order logic, proven by totally elementary means. If P is any property defined over the collection of all first-order t...
103
click to vote
NIPS
1998
15 years 1 months ago
1998
A simple learning rule is derived, the VAPS algorithm, which can be instantiated to generate a wide range of new reinforcementlearning algorithms. These algorithms solve a number ...
CORR
2010
Springer
14 years 12 months ago
2010
Springer
We consider CSP from the point of view of the algebraic theory of effects, which classifies operations as effect constructors and effect deconstructors; it also provides a link wit...
101
click to vote
ATAL
2007
Springer
15 years 6 months ago
2007
Springer
Planning in single-agent models like MDPs and POMDPs can be carried out by resorting to Q-value functions: a (near-) optimal Q-value function is computed in a recursive manner by ...
ICIP
2008
IEEE
16 years 1 months ago
2008
IEEE
In this paper, we present a long term learning system for content based image retrieval over a network. Relevant feedback is used among different sessions to learn both the simila...