Sciweavers

2333 search results - page 294 / 467
» Recursive Computational Depth
Sort
View
AAAI
1996
13 years 9 months ago
Learning to Take Actions
We formalize a model for supervised learning of action strategies in dynamic stochastic domains and show that PAC-learning results on Occam algorithms hold in this model as well. W...
Roni Khardon
IJCAI
1993
13 years 9 months ago
Using Classification as a Programming Language
Our experience in the IDAS natural language generation project has shown us that IDAS'S KLONE-like classifier, originally built solely to hold a domain knowledge base, could ...
Chris Mellish, Ehud Reiter
AAAI
1990
13 years 9 months ago
Symbolic Probabilistic Inference in Belief Networks
The Symbolic Probabilistic Inference (SPI) Algorithm [D'Ambrosio, 19891 provides an efficient framework for resolving general queries on a belief network. It applies the conc...
Ross D. Shachter, Bruce D'Ambrosio, Brendan Del Fa...
GECCO
2008
Springer
170views Optimization» more  GECCO 2008»
13 years 9 months ago
Evolving prediction weights using evolution strategy
The evolution strategy is one of the strongest evolutionary algorithms for optimizing real-value vectors. In this paper, we study how to use it for the evolution of prediction wei...
Trung Hau Tran, Cédric Sanza, Yves Duthen
CACM
2010
113views more  CACM 2010»
13 years 8 months ago
Reasoning about the unknown in static analysis
Static program analysis techniques cannot know certain values, such as the value of user input or network state, at analysis time. While such unknown values need to be treated as ...
Isil Dillig, Thomas Dillig, Alex Aiken