Title : Intuitive Action Set Formation in Learning Classifier Systems with Memory Registers

Presenter Martijn Schut
Abstract An important design goal in Learning Classifier Systems (LCS) is to equally reinforce those classifiers which cause the level of reward supplied by the environment. In this paper, we propose a new method for action set formation in LCS. When applied to a Zeroth Level Classifier System with Memory registers (ZCSM), our method allows the distribution of rewards among classifiers which result in the same memory state, rather than those encoding the same memory update action.

Title : The OKKAM project: the quest for a web of uniquely identified entities

Presenter Stefano Bocconi
Abstract This talk will present the OKKAM project, which aims at providing unique identifiers for all entities (concepts, persons, places, etc.) so that information can be unambiguously associated to them. This project creates theoretical (e.g. what do we choose to be an entity) as well as practical (e.g. performances) challenges, which will be discussed during the talk. Also the consequences for the Semantic Web and the possible relations with other research initiatives will be presented. Given the fact that the project is just started, the presentation will try to stimulate feedback on the key problems which are still under discussion, as well as hopefully start some collaborations with interested parties.