2027 search results - page 1 / 406 » Learning and Generalization with the Information Bottleneck |
ALT
2008
Springer
14 years 2 months ago
2008
Springer
UAI
2003
13 years 6 months ago
2003
Learning with hidden variables is a central challenge in probabilistic graphical models that has important implications for many real-life problems. The classical approach is usin...
FLAIRS
2007
13 years 7 months ago
2007
Using information from failures to guide subsequent search is an important technique for solving combinatorial problems in domains such as boolean satisfiability (SAT) and constr...
LATIN
2004
Springer
13 years 10 months ago
2004
Springer
This paper presents a new mathematical model of AIMD (Additive Increase Multiplicative Decrease) TCP for general networks that we believe is better than those previously used when...
NIPS
2003
13 years 6 months ago
2003
We argue that K–means and deterministic annealing algorithms for geometric clustering can be derived from the more general Information Bottleneck approach. If we cluster the ide...