Toward a multi-strategy and cooperative discovery system
Ning Zhong, Setsuo Ohsuga · 1995
We have been developing a methodology/system called GLS (Global Learning Scheme) for knowledge discovery in databases. The development of GLS has two main aspects. The first is to develop a m&i-strategy system. That is, many kinds of discov-ery/learning methods are cooperatively used in multi-ple learning phases for performing multi-aspect intel-ligent data analysis as well as multi-level conceptual abstraction and learning. As a multi-strategy system, GLS is implemented as a toolkit composed of sev-eral sub-systems and optional parts with a multi-level structure. We have finished main parts belonging to this aspect, and have undertaken another aspect, i.e., extending GLS into a multi-agent, distributed and co-operative discovery system. We try to increase ver-satility and autonomy of GLS by multi-strategy and distributed cooperation, This paper briefly discusses these two aspects of GLS.