Title :
Learning in certainty-factor-based multilayer neural networks for classification
Author_Institution :
Dept. of Comput. & Inf. Sci., Florida Univ., Gainesville, FL, USA
fDate :
1/1/1998 12:00:00 AM
Abstract :
The computational framework of rule-based neural networks inherits from the neural network and the inference engine of an expert system. In one approach, the network activation function is based on the certainty factor (CF) model of MYCIN-like systems. In this paper, it is shown theoretically that the neural network using the CF-based activation function requires relatively small sample sizes for correct generalization. This result is also confirmed by empirical studies in several independent domains
Keywords :
computational complexity; expert systems; feedforward neural nets; generalisation (artificial intelligence); inference mechanisms; learning (artificial intelligence); pattern classification; certainty-factor; expert system; generalization; inference engine; machine learning; multilayer neural networks; rule-based neural networks; sample complexity; Computer architecture; Computer networks; Engines; Expert systems; Intelligent networks; Machine learning; Multi-layer neural network; Multilayer perceptrons; Neural networks; Training data;
Journal_Title :
Neural Networks, IEEE Transactions on
