Sciweavers

427 search results - page 58 / 86
» On the Power of Labels in Transition Systems
Sort
View
ECCV
2008
Springer
16 years 1 months ago
Weakly Supervised Object Localization with Stable Segmentations
Multiple Instance Learning (MIL) provides a framework for training a discriminative classifier from data with ambiguous labels. This framework is well suited for the task of learni...
Carolina Galleguillos, Boris Babenko, Andrew Rabin...
POPL
2007
ACM
16 years 2 days ago
A very modal model of a modern, major, general type system
We present a model of recursive and impredicatively quantified types with mutable references. We interpret in this model all of the type constructors needed for typed intermediate...
Andrew W. Appel, Christopher D. Richards, Jé...
SIGCOMM
2006
ACM
15 years 5 months ago
Algorithms to accelerate multiple regular expressions matching for deep packet inspection
There is a growing demand for network devices capable of examining the content of data packets in order to improve network security and provide application-specific services. Most...
Sailesh Kumar, Sarang Dharmapurikar, Fang Yu, Patr...
LICS
2005
IEEE
15 years 5 months ago
Proof-Theoretic Approach to Description-Logic
In recent work Baader has shown that a certain description logic with conjunction, existential quantification and with circular definitions has a polynomial time subsumption pro...
Martin Hofmann
GECCO
2005
Springer
130views Optimization» more  GECCO 2005»
15 years 5 months ago
ATNoSFERES revisited
ATNoSFERES is a Pittsburgh style Learning Classifier System (LCS) in which the rules are represented as edges of an Augmented Transition Network. Genotypes are strings of tokens ...
Samuel Landau, Olivier Sigaud, Marc Schoenauer