Incremental backpropagation learning networks

How to learn new knowledge without forgetting old knowledge is a key issue in designing an incremental-learning neural network. In this paper, we present a new incremental learning method for pattern recognition, called the "incremental backpropagation learning network", which employs bounded weight modification and structural adaptation learning rules and applies initial knowledge to constrain the learning process. The viability of this approach is demonstrated for classification problems including the iris and the promoter domains.

[1]  Donald F. Specht,et al.  Probabilistic neural networks and the polynomial Adaline as complementary techniques for classification , 1990, IEEE Trans. Neural Networks.

[2]  Youshen Xia,et al.  Neural network for solving linear programming problems with bounded variables , 1995, IEEE Trans. Neural Networks.

[3]  LiMin Fu,et al.  Neural networks in computer intelligence , 1994 .

[4]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[5]  Stephen Grossberg,et al.  Fuzzy ARTMAP: A neural network architecture for incremental supervised learning of analog multidimensional maps , 1992, IEEE Trans. Neural Networks.

[6]  Geoffrey E. Hinton.  Connectionist Learning Procedures , 1989, Artif. Intell..

[7]  John J. Paulos,et al.  A neural network learning algorithm tailored for VLSI implementation , 1994, IEEE Trans. Neural Networks.

[8]  Li-Min Fu.  Knowledge-based connectionism for revising domain theories , 1993, IEEE Trans. Syst. Man Cybern..

[9]  Tsu-Chang Lee,et al.  Structure level adaptation for artificial neural networks , 1991 .

[10]  Jude Shavlik,et al.  Refinement ofApproximate Domain Theories by Knowledge-Based Neural Networks , 1990, AAAI.

[11]  David Haussler,et al.  What Size Net Gives Valid Generalization? , 1989, Neural Computation.

[12]  Susan I. Hruska,et al.  Back-propagation learning in expert networks , 1992, IEEE Trans. Neural Networks.

[13]  Robert J. Marks,et al.  An adaptively trained neural network , 1991, IEEE Trans. Neural Networks.