An upper bound to error probability has been presented in terms of Shannon entropy [6]. In this paper, we obtain Fano's bound for probability based on Renyi's entropy [5]. Further, lower bound for average probability of error is calculated in terms of channel capacity.
Fano’s Inequality for Probability based on Renyl’s Information
17 Views
0 Downloads
Published 2005-04-30
Pages 58-63
Abstract
References
- Ash R., Information Theory, Interscience Publishers, New York 1968.
- Erdogmus D. and Principe J.C., “Information Transfer Through Classifiers and its Relation to Probability of Error”, Intl. Joint Conf. On Neural Networks, pp. 50-54, July 2001.
- Hellman M.E. and Raviv J., “Probability of Error, Equivocation and the Chernoff Bound”, IEEE Trans. Inform. Theory, vol. IT 16, pp. 368-372, 1970.
- Lainiotis D.G., “A Class of Upper Bounds on Probability of Error for Multihypothesis Pattern Recognition”, IEEE Trans. Inform. Theory, vol. IT 15, pp. 730-731, 1969.
- Renyi A., “On Measures of Entropy and Information”, in Proc. 4th Berkeley Symp. Math. And Probability, vol. 1, pp. 547-561, 1960.
- Shannon C.E., “A Mathematical Theory of Communication”, Bell System Tech. Journal, vol. 27, 379-423, 1948.
✓ Citation copied to clipboard