Transductive Confidence Machines for Pattern Recognition

作者: Kostas Proedrou , Ilia Nouretdinov , Volodya Vovk , Alex Gammerman

DOI: 10.1007/3-540-36755-1_32

关键词:

摘要: We propose a new algorithm for pattern recognition that outputs some measures of "reliability" every prediction made, in contrast to the current algorithms output "bare" predictions only. Our method uses rule similar nearest neighbours infer predictions; thus its predictive performance is close neighbours, while confidence it provide practically useful information individual predictions.

参考文章(13)
Ilia Nouretdinov, Thomas Melluish, Volodya Vovk, Ridge Regression Confidence Machine international conference on machine learning. pp. 385- 392 ,(2001)
Harris Papadopoulos, Kostas Proedrou, Volodya Vovk, Alex Gammerman, Inductive Confidence Machines for Regression Lecture Notes in Computer Science. pp. 345- 356 ,(2002) , 10.1007/3-540-36755-1_29
Nello Cristianini, J Shawe-Taylor, An introduction to Support Vector Machines Cambridge University Press (2000). ,(2000)
Thomas Melluish, Craig Saunders, Ilia Nouretdinov, Volodya Vovk, None, Comparing the Bayes and typicalness frameworks european conference on machine learning. pp. 360- 371 ,(2001) , 10.1007/3-540-44795-4_31
R. D. KING, C. FENG, A. SUTHERLAND, STATLOG: COMPARISON OF CLASSIFICATION ALGORITHMS ON LARGE REAL-WORLD PROBLEMS Applied Artificial Intelligence. ,vol. 9, pp. 289- 333 ,(1995) , 10.1080/08839519508945477
Vladimir Naumovich Vapnik, Vlamimir Vapnik, Statistical learning theory John Wiley & Sons. ,(1998)
Ilia Nouretdinov, Volodya Vovk, Michael Vyugin, Alex Gammerman, None, Pattern Recognition and Density Estimation under the General i.i.d. Assumption european conference on computational learning theory. pp. 337- 353 ,(2001) , 10.1007/3-540-44581-1_22