Title :
Building an accretive authentication system using a RBF network
Author :
Zhu, Qiuming ; Liu, Luzheng
Author_Institution :
Digital Imaging & Comput. Vision Lab., Nebraska Univ., Omaha, NE, USA
Abstract :
A computerized authentication system should be able to admit new authentic entries continuously while maintain the existing entry records and an uninterrupted system operation. In this paper, we describe a competitive RBF neural network that is able to incrementally construct itself in response to the pattern samples presented to the system. The neural network is thus a suitable choice for authentication system applications. The accretion property of the neural network is made possible by allowing each pattern class (an authentic entry) being modeled in multiple hyper-ellipsoidal distributions, and mapping these distributions to multiple RBF neural units
Keywords :
learning (artificial intelligence); message authentication; pattern classification; pattern matching; radial basis function networks; accretive authentication system; competitive RBF neural network; computerized authentication system; hyper-ellipsoidal distributions; learning; pattern classification; pattern matching; Application software; Authentication; Computer vision; Digital images; Distribution functions; Laboratories; Neural networks; Neurons; Pattern classification; Radial basis function networks;
Conference_Titel :
Neural Networks, 1999. IJCNN '99. International Joint Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-5529-6
DOI :
10.1109/IJCNN.1999.833541
