Title :
A concept learning network based on correlation and backpropagation
Author_Institution :
Dept. of Comput. & Inf. Sci., Florida Univ., Gainesville, FL, USA
fDate :
12/1/1999 12:00:00 AM
Abstract :
A new concept learning neural network is presented. This network builds correlation learning into a rule learning neural network where the certainty factor model of traditional expert systems is taken as the network activation function. The main argument for this approach is that correlation learning can help when the neural network fails to converge to the target concept due to insufficient or noisy training data. Both theoretical analysis and empirical evaluation are provided to validate the system
Keywords :
backpropagation; expert systems; learning (artificial intelligence); certainty factor model; concept learning; correlation learning; expert systems; network activation function; neural network; rule learning neural network; Backpropagation; Biological neural networks; Expert systems; Hebbian theory; Multi-layer neural network; Multilayer perceptrons; Neural networks; Neurons; Principal component analysis; Training data;
Journal_Title :
Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on
DOI :
10.1109/3477.809045
