Sciweavers

35 search results - page 6 / 7
» Learning in a Fixed or Evolving Network of Agents
Sort
View
AAAI
1994
13 years 9 months ago
Solution Reuse in Dynamic Constraint Satisfaction Problems
Many AI problems can be modeled as constraint satisfaction problems (CSP), but many of them are actually dynamic: the set of constraints to consider evolves because of the environ...
Gérard Verfaillie, Thomas Schiex
KDD
2004
ACM
162views Data Mining» more  KDD 2004»
14 years 8 months ago
Discovering Links Between Lexical and Surface Features in Questions and Answers
Information retrieval systems, based on keyword match, are evolving to question answering systems that return short passages or direct answers to questions, rather than URLs point...
Soumen Chakrabarti
AAAI
2011
12 years 7 months ago
User-Controllable Learning of Location Privacy Policies With Gaussian Mixture Models
With smart-phones becoming increasingly commonplace, there has been a subsequent surge in applications that continuously track the location of users. However, serious privacy conc...
Justin Cranshaw, Jonathan Mugan, Norman M. Sadeh
GECCO
2004
Springer
155views Optimization» more  GECCO 2004»
14 years 1 months ago
Genetic Network Programming with Reinforcement Learning and Its Performance Evaluation
A new graph-based evolutionary algorithm named “Genetic Network Programming, GNP” has been proposed. GNP represents its solutions as directed graph structures, which can improv...
Shingo Mabu, Kotaro Hirasawa, Jinglu Hu
IJCNN
2008
IEEE
14 years 2 months ago
Neuro-visual control in the Quake II game engine
— The first-person-shooter Quake II is used as a platform to test neuro-visual control and retina input layouts. Agents are trained to shoot a moving enemy as quickly as possibl...
Matt Parker, Bobby D. Bryant