Sciweavers

3556 search results - page 219 / 712
» Can machine learning be secure
Sort
View
176
Voted

Publication
152views
15 years 4 months ago
Expected loss analysis of thresholded authentication protocols in noisy conditions
A number of authentication protocols have been proposed recently, where at least some part of the authentication is performed during a phase, lasting $n$ rounds, with no error corr...
Christos Dimitrakakis, Aikaterini Mitrokotsa, Serg...
ICML
2009
IEEE
16 years 1 months ago
Efficient learning algorithms for changing environments
We study online learning in an oblivious changing environment. The standard measure of regret bounds the difference between the cost of the online learner and the best decision in...
Elad Hazan, C. Seshadhri
137
Voted
ACML
2009
Springer
15 years 5 months ago
Learning Algorithms for Domain Adaptation
A fundamental assumption for any machine learning task is to have training and test data instances drawn from the same distribution while having a sufficiently large number of tra...
Manas A. Pathak, Eric Nyberg
120
Voted
SIGCSE
2008
ACM
153views Education» more  SIGCSE 2008»
14 years 11 months ago
A cross-domain visual learning engine for interactive generation of instructional materials
We present the design and development of a Visual Learning Engine, a tool that can form the basis for interactive development of visually rich teaching and learning modules across...
K. R. Subramanian, T. Cassen
96
Voted
ICML
2008
IEEE
16 years 1 months ago
No-regret learning in convex games
Quite a bit is known about minimizing different kinds of regret in experts problems, and how these regret types relate to types of equilibria in the multiagent setting of repeated...
Geoffrey J. Gordon, Amy R. Greenwald, Casey Marks