Sciweavers

3274 search results - page 536 / 655
» Using Learning in a Control Agent
Sort
View
IDEAL
2005
Springer
14 years 2 months ago
Neural Networks: A Replacement for Gaussian Processes?
Abstract. Gaussian processes have been favourably compared to backpropagation neural networks as a tool for regression. We show that a recurrent neural network can implement exact ...
Matthew Lilley, Marcus R. Frean
ATAL
2004
Springer
14 years 2 months ago
Run the GAMUT: A Comprehensive Approach to Evaluating Game-Theoretic Algorithms
We present GAMUT1 , a suite of game generators designed for testing game-theoretic algorithms. We explain why such a generator is necessary, offer a way of visualizing relationshi...
Eugene Nudelman, Jennifer Wortman, Yoav Shoham, Ke...
HIS
2008
13 years 10 months ago
Towards a Highly Scalable Hybrid Metaheuristic for Haplotype Inference Under Parsimony
Haplotype Inference is a challenging problem in bioinformatics that consists in inferring the basic genetic constitution of diploid organisms on the basis of their genotype. This ...
Stefano Benedettini, Luca Di Gaspero, Andrea Roli
MRC
2003
182views Robotics» more  MRC 2003»
13 years 10 months ago
Virtual Synergy: A Human-Robot Interface for Urban Search and Rescue
This paper describes the Virtual Synergy interface, which combines a three dimensional graphical interface with physical robots to allow for collaboration among multiple human res...
Sheila Tejada, Andrew Cristina, Priscilla Goodwyne...
IJCAI
1989
13 years 10 months ago
Execution Architectures and Compilation
This paper introduces a partition of the possible forms of knowledge according to their rela­ tionship to the basic objective of an intelligent agent, namely to act successfully ...
Stuart J. Russell