Sciweavers

388 search results - page 27 / 78
» The covering number in learning theory
Sort
View
FOCI
2007
IEEE
14 years 1 months ago
Almost All Learning Machines are Singular
— A learning machine is called singular if its Fisher information matrix is singular. Almost all learning machines used in information processing are singular, for example, layer...
Sumio Watanabe
ATAL
2009
Springer
14 years 2 months ago
Multiagent learning in large anonymous games
In large systems, it is important for agents to learn to act effectively, but sophisticated multi-agent learning algorithms generally do not scale. An alternative approach is to ď...
Ian A. Kash, Eric J. Friedman, Joseph Y. Halpern
SIGECOM
2004
ACM
135views ECommerce» more  SIGECOM 2004»
14 years 24 days ago
Applying learning algorithms to preference elicitation
We consider the parallels between the preference elicitation problem in combinatorial auctions and the problem of learning an unknown function from learning theory. We show that l...
Sébastien Lahaie, David C. Parkes
FOCS
2008
IEEE
14 years 1 months ago
Computing the Tutte Polynomial in Vertex-Exponential Time
The deletion–contraction algorithm is perhaps the most popular method for computing a host of fundamental graph invariants such as the chromatic, flow, and reliability polynomi...
Andreas Björklund, Thore Husfeldt, Petteri Ka...
MMSEC
2006
ACM
148views Multimedia» more  MMSEC 2006»
14 years 1 months ago
Minimizing the embedding impact in steganography
In this paper, we study the trade-off in steganography between the number of embedding changes and their amplitude. We assume that each element of the cover image is assigned a sc...
Jessica J. Fridrich