Title :
A hybrid knowledge processing architecture
Author_Institution :
Tech. Univ. Hamburg-Harburg, Germany
Abstract :
An example of a hybrid system architecture integrating connectionist models and symbolic knowledge processing is introduced. In particular the inclusion of non-symbolic knowledge sources (data from physical processes, measurements, sensors etc.), transformation of learned knowledge into a symbolic form (rule extraction) and associative storage as well as retrieval of information are discussed by means of application examples. Finally, parallel hardware support for the proposed hybrid system architecture is presented
Keywords :
content-addressable storage; knowledge based systems; knowledge representation; neural nets; parallel architectures; symbol manipulation; associative storage; connectionist models; hybrid knowledge processing architecture; information retrieval; nonsymbolic knowledge sources; parallel hardware support; rule extraction; symbolic knowledge processing;
Conference_Titel :
Intelligent Systems Engineering, 1994., Second International Conference on
Conference_Location :
Hamburg-Harburg
Print_ISBN :
0-85296-621-0
DOI :
10.1049/cp:19940653