Abstract
MRI (Madaline Rule I) neural network has wide applications. A finite convergence for the training of MRI neural network is proved for linearly separable training patterns.
Partly supported by the National Natural Science Found of China, the Basic Research Program of the Committee of Science, Technology and Industry of National Defense of China.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Widrow, B., Lehr, M.A.: 30 Years of Adaptive Neural Networks: Perceptron, Madaline, and Backpropagation. Proc. of IEEE 78(9), 1415–1441 (1990)
Hoff, Jr., M.E.: Learning Phenomena in Networks of Adaptive Switching Circuits. Ph.D. thesis, Tech.Rep. 1554-1. Stanford Electron. Labs., Stanford, CA (1962)
Widrow, B., Winter, R., Baxter, R.: Learing Phenomena in Layered Neural Networks. IEEE 1st Conf. on Neural Networks, 411–429 (1987)
Zhu, Q.M., Tawfik, A.Y.: Quantitative Object Motion Prediction by an ART2 and Madaline Combined Neural Network: Concepts and Experiments. Artif. Intell. 8(5), 569–578 (1995)
Piche, S.: Robustness of Feedforward Neural Networks. IJCNN 2, 346–351 (1992)
Oh, S., Lee, Y.: Sensitivity Analysis of Single Hidden Layer Neural Networks with Threshold Functions. Neural Networks 6(4), 1005–1007 (1995)
Stevenson, M., Winter, R., Widrow, B.: Sensitivity of Feedforward Neural Networks to Weight Errors. Neural Networks 1, 71–90 (1990)
Widrow, B., Kamenetsky, M.: On the Statistical Efficiency of the LMS Family of Adaptive Algorithms. IJCNN 4, 2872–2880 (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Liu, L., Wu, W. (2004). Finite Convergence of MRI Neural Network for Linearly Separable Training Patterns. In: Yin, FL., Wang, J., Guo, C. (eds) Advances in Neural Networks – ISNN 2004. ISNN 2004. Lecture Notes in Computer Science, vol 3173. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-28647-9_48
Download citation
DOI: https://doi.org/10.1007/978-3-540-28647-9_48
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22841-7
Online ISBN: 978-3-540-28647-9
eBook Packages: Springer Book Archive