Sciweavers

1180 search results - page 203 / 236
» An Instance Selection Approach to Multiple Instance Learning
Sort
View
TREC
2004
14 years 11 months ago
From the Texts to the Contexts They Contain: A Chain of Linguistic Treatments
The text-mining system we are building deals with the specific problem of identifying the instances of relevant concepts present in the texts. Therefore, our system relies on inte...
Ahmed Amrani, Jérôme Azé, Thom...
GECCO
2005
Springer
153views Optimization» more  GECCO 2005»
15 years 3 months ago
Evolving neural network ensembles for control problems
In neuroevolution, a genetic algorithm is used to evolve a neural network to perform a particular task. The standard approach is to evolve a population over a number of generation...
David Pardoe, Michael S. Ryoo, Risto Miikkulainen
ICCV
2011
IEEE
13 years 9 months ago
N-best maximal decoders for part models
We describe a method for generating N-best configurations from part-based models, ensuring that they do not overlap according to some user-provided definition of overlap. We ext...
Dennis Park, Deva Ramanan
JSAC
2010
138views more  JSAC 2010»
14 years 8 months ago
Dynamic conjectures in random access networks using bio-inspired learning
—Inspired by the biological entities’ ability to achieve reciprocity in the course of evolution, this paper considers a conjecture-based distributed learning approach that enab...
Yi Su, Mihaela van der Schaar
SIGSOFT
2008
ACM
15 years 10 months ago
Javert: fully automatic mining of general temporal properties from dynamic traces
Program specifications are important for many tasks during software design, development, and maintenance. Among these, temporal specifications are particularly useful. They expres...
Mark Gabel, Zhendong Su