Patent
1993-07-02
1995-03-07
Knepper, David D.
395 21, 395 24, 395 27, 395 50, G06F 1518
Patent
active
053965809
ABSTRACT:
A rule-based expert system is generated from a neural network. The neural network is trained in such a way as to avoid redundancy and to select input weights to the various processing elements in such a way as to nullify the input weights which have smaller absolute values. The neural network is translated into a set of rules by a heuristic search technique. Additionally, the translation distinguishes between positive and negative attributes for efficiency and can adequately explore rule size exponential with a given parameter. Both explicit and implicit knowledge of adapted neural networks are decoded and represented as if--then rules.
REFERENCES:
patent: 4914603 (1990-04-01), Wood
patent: 5003490 (1991-03-01), Castelaz et al.
patent: 5073867 (1991-12-01), Murphy et al.
patent: 5218529 (1993-06-01), Meyer et al.
patent: 5222194 (1993-06-01), Nishimura
patent: 5226092 (1993-07-01), Chen
patent: 5241620 (1993-08-01), Rugglero
patent: 5251268 (1993-10-01), Colley et al.
Ravichandran et al, "A two-stage neural network for translation, rotation, and size-invariant visual pattern recognition"; ICASSP 91, pp. 2393-2396, vol. 4, 14-17 Apr. 1991.
Hafiz Tariq
Knepper David D.
University of Florida
LandOfFree
Translation of a neural network into a rule-based expert system does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Translation of a neural network into a rule-based expert system, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Translation of a neural network into a rule-based expert system will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1413026