Sciweavers

502 search results - page 35 / 101
» Distributed Learning with Biogeography-Based Optimization
Sort
View
CVPR
2007
IEEE
14 years 12 months ago
Adaptive Patch Features for Object Class Recognition with Learned Hierarchical Models
We present a hierarchical generative model for object recognition that is constructed by weakly-supervised learning. A key component is a novel, adaptive patch feature whose width...
Fabien Scalzo, Justus H. Piater
GECCO
2007
Springer
172views Optimization» more  GECCO 2007»
14 years 4 months ago
A simulation of evolved autotrophic reproduction
In this experiment we evolve reproductive behaviors for a simulated vehicle. Future work will employ the resulting behaviors to populate a simulated ecosystem. Categories and Subj...
Correy Allen Kowall, Brian J. Krent
ICML
2006
IEEE
14 years 10 months ago
Nightmare at test time: robust learning by feature deletion
When constructing a classifier from labeled data, it is important not to assign too much weight to any single input feature, in order to increase the robustness of the classifier....
Amir Globerson, Sam T. Roweis
ICML
1995
IEEE
14 years 10 months ago
Ant-Q: A Reinforcement Learning Approach to the Traveling Salesman Problem
In this paper we introduce Ant-Q, a family of algorithms which present many similarities with Q-learning (Watkins, 1989), and which we apply to the solution of symmetric and asymm...
Luca Maria Gambardella, Marco Dorigo
GECCO
2007
Springer
143views Optimization» more  GECCO 2007»
14 years 4 months ago
Learning and exploiting knowledge in multi-agent task allocation problems
Imagine a group of cooperating agents attempting to allocate tasks amongst themselves without knowledge of their own capabilities. Over time, they develop a belief of their own sk...
Adam Campbell, Annie S. Wu