Experimental performance studies on computer systems, including Grids, require deep understandings on their workload characteristics. The need arises from two important and closel...
— In connectionist learning, one relevant problem is “catastrophic forgetting” that may occur when a network, trained with a large set of patterns, has to learn new input pat...
Dario Albesano, Roberto Gemello, Pietro Laface, Fr...
We propose an active vision system for object acquisition. The core of our approach is a reinforcement learning module which learns a strategy to scan an object. The agent moves a...
Gabriele Peters, Claus-Peter Alberts, Markus Bries...
ys when planning meant searching for a sequence of abstract actions that satisfied some symbolic predicate. Robots can now learn their own representations through statistical infe...
This poster presentation introduces our first Squeak workshops offered in the context of the ALAN-K (Advanced LeArning Network in Kyoto) project (Konomi and Karuno, 2003), which i...