Sciweavers

414 search results - page 38 / 83
» Discrete Optimization via Simulation Using COMPASS
Sort
View
NIPS
2007
13 years 11 months ago
Multi-Task Learning via Conic Programming
When we have several related tasks, solving them simultaneously is shown to be more effective than solving them individually. This approach is called multi-task learning (MTL) and...
Tsuyoshi Kato, Hisashi Kashima, Masashi Sugiyama, ...
AI
1999
Springer
13 years 9 months ago
Cooperative Behavior Acquisition for Mobile Robots in Dynamically Changing Real Worlds Via Vision-Based Reinforcement Learning a
In this paper, we first discuss the meaning of physical embodiment and the complexity of the environment in the context of multi-agent learning. We then propose a vision-based rei...
Minoru Asada, Eiji Uchibe, Koh Hosoda
CVPR
2008
IEEE
14 years 12 months ago
Object tracking and detection after occlusion via numerical hybrid local and global mode-seeking
Given an object model and a black-box measure of similarity between the model and candidate targets, we consider visual object tracking as a numerical optimization problem. During...
Zhaozheng Yin, Robert T. Collins
INFOCOM
2002
IEEE
14 years 2 months ago
Optimal on-line estimation of the size of a dynamic multicast group
Abstract—In this paper we propose an efficient on-line estimation algorithm for determining the size of a dynamic multicast group. By using diffusion approximation and Kalman ...
Sara Alouf, Eitan Altman, Philippe Nain
MASCOTS
2008
13 years 11 months ago
Modeling Software Contention using Colored Petri Nets
Commercial servers, such as database or application servers, often attempt to improve performance via multithreading. Improper multi-threading architectures can incur contention, ...
Nilabja Roy, Akshay Dabholkar, Nathan Hamm, Lawren...