Sciweavers

1160 search results - page 188 / 232
» Dynamic Programming Algorithm for Training Functional Networ...
Sort
View
ML
1998
ACM
101views Machine Learning» more  ML 1998»
15 years 1 months ago
Elevator Group Control Using Multiple Reinforcement Learning Agents
Recent algorithmic and theoretical advances in reinforcement learning (RL) have attracted widespread interest. RL algorithmshave appeared that approximatedynamic programming on an ...
Robert H. Crites, Andrew G. Barto
JCSS
2008
81views more  JCSS 2008»
15 years 2 months ago
A simulator for adaptive parallel applications
Dynamically allocating computing nodes to parallel applications is a promising technique for improving the utilization of cluster resources. Detailed simulations can help identify...
Basile Schaeli, Sebastian Gerlach, Roger D. Hersch
CVIU
2011
14 years 5 months ago
Graph-based quadratic optimization: A fast evolutionary approach
Quadratic optimization lies at the very heart of many structural pattern recognition and computer vision problems, such as graph matching, object recognition, image segmentation, ...
Samuel Rota Bulò, Marcello Pelillo, Immanue...
CSFW
2007
IEEE
15 years 8 months ago
Creating Vulnerability Signatures Using Weakest Preconditions
Signature-based tools such as network intrusion detection systems are widely used to protect critical systems. Automatic signature generation techniques are needed to enable these...
David Brumley, Hao Wang, Somesh Jha, Dawn Xiaodong...
ISAAC
2005
Springer
123views Algorithms» more  ISAAC 2005»
15 years 7 months ago
Sampling Unlabeled Biconnected Planar Graphs
We present an expected polynomial time algorithm to generate a 2-connected unlabeled planar graph uniformly at random. To do this we first derive recurrence formulas to count the ...
Manuel Bodirsky, Clemens Gröpl, Mihyun Kang