Abstract
In this paper, the progress, human learns from the outside world by image and graph, is described by stochastic graph. Markov model is given for the learning process in neural network. Then a method of computation transition matrix is presented via energy function. Based on transition matrix, probability of state is computed and implemented to cognize the objective world by stochastic graph. By applying stochastic graph to the network of two neurons, it shows that states can transform between each other. Finally, the network updates to the state of the least energy.
The research was supported by National Basic Research Program of China (973 Program) under grant No. 2003CB517106
This is a preview of subscription content, log in via an institution to check access.
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
Kim, L.: Proposed Model of Human Consciousness System with Applications in Pattern Recognition. In: Proceedings of the International Conference on Knowledge-Based Intelligent Electronic Systems, KES 1997, pp. 159–166 (1997)
Ewert, J.P.: An Introduction to the Neurophysiological Fundamentals of Behavior. Springer, New York (1980)
Xi, G.C.: A Tentative Investigation of the Learning Process of a Neural Network System. Acta Automation Sinica 17, 331–316 (1991)
Burnod, Y., et al.: Cooperation Between Learning Rules in the Cerebro-cerebellar Neural Network. Neural Network World 14, 207–220 (2004)
Biondi, E., Guardabassi, G., Kinaldi, S.: On the analysis of Markovian Discrete by Means of Stochastic Graphs. Automation and Remote Control 28, 275–277 (1967)
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
Zhao, Y., Xi, G., Yi, J. (2005). Study Markov Neural Network by Stochastic Graph. In: Wang, J., Liao, X., Yi, Z. (eds) Advances in Neural Networks – ISNN 2005. ISNN 2005. Lecture Notes in Computer Science, vol 3496. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11427391_88
Download citation
DOI: https://doi.org/10.1007/11427391_88
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-25912-1
Online ISBN: 978-3-540-32065-4
eBook Packages: Computer ScienceComputer Science (R0)