Showing papers by "Zhi-Hua Zhou published in 2000"

Pose invariant face recognition

Abstract: We describe a novel neural network architecture, which can recognize human faces with any view in a certain viewing angle range (from left 30 degrees to right 30 degrees out of plane rotation). View-specific eigenface analysis is used as the front-end of the system to extract features, and the neural network ensemble is used for recognition. Experimental results show that the recognition accuracy of our network ensemble is higher than conventional methods such as using a single neural network to recognize faces of a specific view.

FANNC: a fast adaptive neural network classifier

Abstract: In this paper, a fast adaptive neural network classifier named FANNC is proposed. FANNC exploits the advantages of both adaptive resonance theory and field theory. It needs only one-pass learning, and achieves not only high predictive accuracy but also fast learning speed. Besides, FANNC has incremental learning ability. When new instances are fed, it does not need to retrain the whole training set. Instead, it could learn the knowledge encoded in those instances through slightly adjusting the network topology when necessary, that is, adaptively appending one or two hidden units and corresponding connections to the existing network. This characteristic makes FANNC fit for real-time online learning tasks. Moreover, since the network architecture is adaptively set up, the disadvantage of manually determining the number of hidden units of most feed-forward neural networks is overcome. Benchmark tests show that FANNC is a preferable neural network classifier, which is superior to several other neural algorithms on both predictive accuracy and learning speed.

Using neural networks for fault diagnosis

Abstract: A universal fault instance model, which aims to solve problems existing in the present technology of fault diagnosis, such as the lack of universality, the difficulty in the use of real time systems and the dilemma of stability and plasticity, is proposed. An experiment demonstrates that the FANNC used can successfully settle the problems mentioned above by its effective incremental ability and processing new input patterns via one round learning.

A statistics based approach for extracting priority rules from trained neural networks

Abstract: In this paper, a statistics based approach named STARE (statistics-based rule extraction) that is designed to extract symbolic rules from trained neural networks is proposed. STARE deals with continuous attributes in a unique way so that not only different attributes could be discretized to different number of clusters but also unnecessary discretization could be avoided. STARE introduces statistics to the generation and evaluation of priority rules that have concise appearance. Since it is independent of the network architectures and training algorithms, STARE could be applied to diversified neural classifiers. Experimental results show that rules extracted via STARE are comprehensible, compact and accurate.