Hybrid Systems for Meta-Learning (Part II): the MINDFUL System
Ciro Castiello, Anna Maria Fanelli · 2006
For pt. I see ibid., (2005). In this paper we investigate the application feasibilities of hybrid systems in meta-learning contexts with a practical perspective. In particular, we present the MINDFUL system, which represents a particular framework for meta-learning founded on the integration of connectionist paradigms and fuzzy knowledge management. The peculiar organisation of the system allows to exploit it on different levels of application, being able to employ the accumulated learning experience in cross-task contexts. The evaluation of MINDFUL is detailed through a set of experimental sessions