|
|
A SEQUENTIAL LEARNING ALGORITHM OF NEURAL NETWORK AND ITS APPLICATION |
Deng Chao①; Xiong Fanlun①; Tan Ying②; He Zhenya② |
①Uni. of Sci. and Tech. of China & the Inst. oflntell. Machines; Academia Sinica; Hefei230027;②Department of Radio Engineering; Southeast University; Nanjing 210096 |
|
|
Abstract In this paper we propose a sequential learning neural net which consists of the bounded weight adjustment algorithm and structure adaptive adjustment method. This network is characterized of efficiently learning the knowledge of new samples in series. After we present an efficient sequential learning algorithm of this network, we analyze its learning feature and recognition performance in detail. The effectiveness of this network have also been shown by theoretical analyses and a lot of experiments in this paper.
|
Received: 23 March 1998
|
|
|
|
|
|
|
|