Sciweavers

3556 search results - page 141 / 712
» Can machine learning be secure
Sort
View
COLT
2001
Springer
14 years 3 months ago
Agnostic Boosting
We prove strong noise-tolerance properties of a potential-based boosting algorithm, similar to MadaBoost (Domingo and Watanabe, 2000) and SmoothBoost (Servedio, 2003). Our analysi...
Shai Ben-David, Philip M. Long, Yishay Mansour
OOPSLA
1995
Springer
14 years 2 months ago
Using a Prototype-based Language for User Interface: The Newton Project's Experience
Object-oriented user interface frameworks are usually implemented in a class-based language. We chose instead to develop a prototype-based language, NewtonScript, for this purpose...
Walter R. Smith
COLT
2006
Springer
14 years 2 months ago
Online Learning with Variable Stage Duration
We consider online learning in repeated decision problems, within the framework of a repeated game against an arbitrary opponent. For repeated matrix games, well known results esta...
Shie Mannor, Nahum Shimkin
STACS
1999
Springer
14 years 2 months ago
Costs of General Purpose Learning
Leo Harrington surprisingly constructed a machine which can learn any computable function f according to the following criterion (called Bc∗ -identification). His machine, on t...
John Case, Keh-Jiann Chen, Sanjay Jain
ML
2010
ACM
155views Machine Learning» more  ML 2010»
13 years 9 months ago
On the infeasibility of modeling polymorphic shellcode - Re-thinking the role of learning in intrusion detection systems
Current trends demonstrate an increasing use of polymorphism by attackers to disguise their exploits. The ability for malicious code to be easily, and automatically, transformed in...
Yingbo Song, Michael E. Locasto, Angelos Stavrou, ...