We present a new family of subgradient methods that dynamically incorporate knowledge of the geometry of the data observed in earlier iterations to perform more informative gradie...
We describe a system that successfully transfers value function knowledge across multiple subdomains of realtime strategy games in the context of multiagent reinforcement learning....
How can artificial neural nets generalize better from fewer examples? In order to generalize successfully, neural network learning methods typically require large training data se...
This paper presents my participation to the second Morpho Challenge. Results have been obtained with the algorithm already presented at Morpho Challenge 2005. The system takes a p...
The performance of many supervised and unsupervised learning algorithms is very sensitive to the choice of an appropriate distance metric. Previous work in metric learning and ada...