Title :
A neural network model which combines unsupervised and supervised learning
Author :
Hsieh, Keun-Rong ; Chen, Wen-Tsuen
Author_Institution :
Dept. of Comput. Sci., Nat. Tsing Hua Univ., Hsinchu, Taiwan
fDate :
3/1/1993 12:00:00 AM
Abstract :
A neural network that combines unsupervised and supervised learning for pattern recognition is proposed. The network is a hierarchical self-organization map, which is trained by unsupervised learning at first. When the network fails to recognize similar patterns, supervised learning is applied to teach the network to give different scaling factors for different features so as to discriminate similar patterns. Simulation results show that the model obtains good generalization capability as well as sharp discrimination between similar patterns
Keywords :
learning (artificial intelligence); neural nets; pattern recognition; hierarchical self-organization map; neural network model; pattern recognition; scaling factors; supervised learning; unsupervised learning; Artificial neural networks; Error correction; Feature extraction; Neural networks; Neurofeedback; Pattern recognition; Signal generators; Steady-state; Supervised learning; Unsupervised learning;
Journal_Title :
Neural Networks, IEEE Transactions on
