DocumentCode :
2585156
Title :
A neural computer architecture for data exploration
Author :
Bykhovsky, V. ; Grinstein, Georges ; Lou, Jian
Author_Institution :
Dept. of Comput. Sci., Massachusetts Univ., Lowell, MA, USA
fYear :
1991
fDate :
13-16 Oct 1991
Firstpage :
1253
Abstract :
The authors´ approach to problem-solving does not require a formal, symbolic mathematical model. It is based on interactive experimentation, interrelating the result data into IF-THEN units, data generalization and data-driven reasoning. It can be applied to the exploration of real-word hard-to-formalize data-intensive problems such as traffic control, environmental forecasting, military reconnaissance, technical and medical diagnosis, robotics, software debugging, and system maintenance. The data-based model, in contrast to a symbolic one, can be stepwise refined using additional input-output pairs to match any given precision or other constraints, a possibility hard to realize in the case of symbolic mathematical models
Keywords :
knowledge based systems; neural nets; parallel architectures; problem solving; IF-THEN units; data exploration; data generalization; data-driven reasoning; environmental forecasting; hard-to-formalize data-intensive problems; input-output pairs; interactive experimentation; medical diagnosis; military reconnaissance; neural computer architecture; problem-solving; robotics; software debugging; stepwise model refinement; system maintenance; technical diagnosis; traffic control; Application software; Buildings; Computer architecture; Computer graphics; Image databases; Neural networks; Problem-solving; Smoothing methods; Traffic control; Vehicles;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Systems, Man, and Cybernetics, 1991. 'Decision Aiding for Complex Systems, Conference Proceedings., 1991 IEEE International Conference on
Conference_Location :
Charlottesville, VA
Print_ISBN :
0-7803-0233-8
Type :
conf
DOI :
10.1109/ICSMC.1991.169859
Filename :
169859
Link To Document :
بازگشت