Sciweavers

1380 search results - page 117 / 276
» On Universal Transfer Learning
Sort
View
TON
2010
167views more  TON 2010»
13 years 4 months ago
A Machine Learning Approach to TCP Throughput Prediction
TCP throughput prediction is an important capability in wide area overlay and multi-homed networks where multiple paths may exist between data sources and receivers. In this paper...
Mariyam Mirza, Joel Sommers, Paul Barford, Xiaojin...
ICRA
2009
IEEE
169views Robotics» more  ICRA 2009»
14 years 4 months ago
Task-level imitation learning using variance-based movement optimization
— Recent advances in the field of humanoid robotics increase the complexity of the tasks that such robots can perform. This makes it increasingly difficult and inconvenient to ...
Manuel Mühlig, Michael Gienger, Sven Hellbach...
ICML
2010
IEEE
13 years 11 months ago
Bayesian Multi-Task Reinforcement Learning
We consider the problem of multi-task reinforcement learning where the learner is provided with a set of tasks, for which only a small number of samples can be generated for any g...
Alessandro Lazaric, Mohammad Ghavamzadeh
WIKIS
2005
ACM
14 years 3 months ago
Wikis in teaching and assessment: the M/Cyclopedia project
In a knowledge-based, networked economy, students leaving university need to have attained skills in collaborative and creative project-based work and to have developed critical, ...
Axel Bruns, Sal Humphreys
COLT
2004
Springer
14 years 3 months ago
Convergence of Discrete MDL for Sequential Prediction
We study the properties of the Minimum Description Length principle for sequence prediction, considering a two-part MDL estimator which is chosen from a countable class of models....
Jan Poland, Marcus Hutter