Title :
A logical architecture for supervised learning
Author :
Healy, Michael J.
Author_Institution :
Boeing Co., Seattle, WA, USA
Abstract :
The author discusses a neural network architecture for supervised learning with inherent stability properties. The architecture uses two ART 1 unsupervised systems with supervision through interconnects. The system will respond as trained under controlled operating conditions, and the use of adaptive resonance provides a means of addressing novel inputs. This and the ability to apply the network as a knowledge system are aided by a formal logic model. The system has potential applications in multisensor analysis, adaptive control, and neural network knowledge systems
Keywords :
adaptive control; formal logic; knowledge based systems; learning systems; neural nets; ART 1; adaptive control; adaptive resonance; formal logic model; knowledge system; logical architecture; multisensor analysis; neural network; supervised learning; Adaptive control; Control systems; Knowledge based systems; Logic; Neural networks; Programmable control; Resonance; Stability; Subspace constraints; Supervised learning;
Conference_Titel :
Neural Networks, 1991. 1991 IEEE International Joint Conference on
Print_ISBN :
0-7803-0227-3
DOI :
10.1109/IJCNN.1991.170402
