Abstract An incremental learning algorithm of a modified minimumdistance classifier is proposed to eliminate the inter disturbance of the classifier during the incremental learning process. It enables the classifier to remember the old knowledge and learn the new one at the same time. Incremental learning requires the modification of the classifier structure, and certain number of old samples must be reserved to help to review old knowledge while learning the new one. In terms of normal distributed sample sets, a new filtering algorithm is proposed. A few samples are preserved which are representative and greatly reduced the cost of storing as well as retraining. Experimental results show that the algorithm gives high rate of recognition correctness. It makes the old samples remain high rate of recognition correctness while the new samples are also effectively recognized with less storing space.
[1] Polikar R, Upda L, Upda S S, et al. Learn++: An Incremental Learning Algorithm for Supervised Neural Networks. IEEE Trans on Systems, Man and Cybernetics, 2001, 31(4): 497508 [2] Marin R, Sanchez J S, Sanz P J. Object Recognition and Incremental Learning Algorithms for a WebBased Telerobotic System // Proc of the IEEE International Conference on Robotics and Automation. Washington, USA, 2002, Ⅲ: 27192724 [3] Okamoto K, Ozawa S, Abe S. A Fast Incremental Learning Algorithm of RBF Networks with LongTerm Memory // Proc of the International Joint Conference on Neural Networks. Oregon, USA, 2003, Ⅰ: 102107 [4] Fu Linmin, Hsu H, Principe J C. Incremental Back Propagation Learning Networks. IEEE Trans on Neural Networks, 1996, 7(3):757761 [5] Yamauchi K, Yamaguchi N, Ishii N. Incremental Learning Methods with Retrieving of Interfered Patterns. IEEE Trans on Neural Networks, 1999, 10(6): 13511365 [6] Nakayama H, Yoshida M. Additional Learning and Forgetting by Potential Method for Pattern Classification // Proc of the International Conference on Neural Networks. Houston, USA, 1997, Ⅲ: 18391844 [7] Li Jinzong. Pattern Recognition Introduction. Beijing, China: Higher Education Press, 1994 (in Chinese) (李金宗.模式识别导论.北京:高等教育出版社,1994) [8] Sun Jixiang. Modern Pattern Recognition. Changsha, China: National Defense Science and Technology University Press, 2002 (in Chinese) (孙即祥.现代模式识别.长沙:国防科技大学出版社,2002) [9] Dasarathy B V. Nearest Neighbor (NN) Norms: NN Pattern Classification Techniques. Los Alamitos, USA: IEEE Computer Society Press, 1991 [10] Duda R O, Hart P E, Stork D G. Pattern Classification. 2nd Edition. New York, USA: John Wiley & Sons, 2001 [11] Hart P E. The Condensed Nearest Neighbor Rule. IEEE Trans on Information Theory, 1968, 14(3): 515516
2007, Vol. 20 
