Abstract
Corner classification (CC) network is a kind of feed forward neural network for instantly document classification. To classify text object instantly, new training algorithm, named as TextCC, for feed forward neural network is presented in this paper. To give a solution for multi-corner judging, new training algorithm for the construction of weight matrix of output layer of CC is given. Experimental results show that TextCC can work well and the precision of TextCC is higher than CC4’s.
This paper was granted financial support from “21st Century Education Revitalization Project” and “China Postdoctoral Science Foundation (2004036463)”.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Shu, B., Kak, S.: A Neural Network-based Intelligent Metasearch Engine. Information Sciences 1, 1–11 (1999)
Chen, E., Zhang, Z., Wang, X.: An Extended Corner Classification Neural Network Based Document Classification Approach. Journal of Software, 871–878 (2002)
Tang, K.W., Kak, S.C.: A New Corner Classification Approach to Neural Network Training. Circuits Systems Signal Processing 17, 459–469 (1998)
Raina, P.: Comparison of Learning and Generalization Capabilities of the Kak and the Back Propagation Algorithms. Information Sciences 81, 261–274 (1994)
Kak, S.: New Algorithms for Training Feed Forward Neural Networks. Pattern Recognition Letters 15, 295–298 (1994)
Kak, S.: On Generalization by Neural Networks. Information Sciences 111, 293–302 (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zhang, Z., Zhang, S., Chen, E., Wang, X., Cheng, H. (2005). TextCC: New Feed Forward Neural Network for Classifying Documents Instantly. In: Wang, J., Liao, XF., Yi, Z. (eds) Advances in Neural Networks – ISNN 2005. ISNN 2005. Lecture Notes in Computer Science, vol 3497. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11427445_37
Download citation
DOI: https://doi.org/10.1007/11427445_37
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-25913-8
Online ISBN: 978-3-540-32067-8
eBook Packages: Computer ScienceComputer Science (R0)