论文信息 - A structurally adaptive neural tree for the recognition of large character set

A structurally adaptive neural tree for the recognition of large character set

This paper presents an adaptive self-organizing neural tree and its application to character recognition. The neural tree is suitable for hierarchical classification and it can grow and shrink to adapt to the changing environment. It also performs parametric adaptation to cope with small changes in the environment. When applied to character pattern recognition, it shows promising performance.<<ETX>>

[1] Ching Y. Suen,et al. Analysis and Design of a Decision Tree Based on Entropy Reduction and Its Application to Large Character Set Recognition , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2] J. R. Quilan. Decision trees and multi-valued attributes , 1988 .

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

[4] David Zipser,et al. Feature Discovery by Competive Learning , 1986, Cogn. Sci..

[5] Yuan Yan Tang,et al. Transformation-Ring-Projection (Trp) Algorithm and its VLSI Implementation , 1991, Int. J. Pattern Recognit. Artif. Intell..

[6] Ethem Alpaydm. Grow-and-Learn: An Incremental Method for Category Learning , 1990 .

[7] Richard P. Lippmann,et al. An introduction to computing with neural nets , 1987 .

[8] Terence D. Sanger,et al. A tree-structured adaptive network for function approximation in high-dimensional spaces , 1991, IEEE Trans. Neural Networks.

[9] Stanley C. Ahalt,et al. Neural Networks for Vector Quantization of Speech and Images , 1990, IEEE J. Sel. Areas Commun..

[10] Allen M. Peterson,et al. Adaptive Vector Quantization Using a Self-Development Neural Network , 1990, IEEE J. Sel. Areas Commun..

[11] Stephen Grossberg,et al. Competitive Learning: From Interactive Activation to Adaptive Resonance , 1987, Cogn. Sci..

[12] Bart Kosko. Stochastic competitive learning , 1991, IEEE Trans. Neural Networks.