Title :
New methods of machine learning for the construction of integrated neuromorphic and associative-memory knowledge bases
Author :
Zografski, Zlatko
Author_Institution :
Div. of Comput. Sci., Univ. Kiril i Metodij, Skopje, Yugoslavia
Abstract :
There is now a consensus that information systems designed to solve problems in complex, dynamic domains will require intelligent use of sophisticated knowledge bases. The construction of such bases through explicit learning is difficult. As a result, various methods of machine learning from examples are tried to alleviate the problem. Experimental evidence is presented on the successful performance of two new learning methods in the acquisition of inverse dynamics models of robot manipulators
Keywords :
content-addressable storage; industrial robots; knowledge based systems; learning systems; neural nets; associative-memory knowledge bases; dynamic domains; information systems; inverse dynamics models; learning methods; machine learning; neural nets; neuromorphic knowledge bases; performance; robot manipulators; Computer networks; Computer science; Intelligent robots; Inverse problems; Learning systems; Machine learning; Manipulator dynamics; Multidimensional systems; Neural networks; Neuromorphics;
Conference_Titel :
Electrotechnical Conference, 1991. Proceedings., 6th Mediterranean
Conference_Location :
LJubljana
Print_ISBN :
0-87942-655-1
DOI :
10.1109/MELCON.1991.162045
