DocumentCode :
3734269
Title :
Why the Naive Bayes approximation is not as Naive as it appears
Author :
Christopher R. Stephens;Hugo Flores Huerta;Ana Ru?z Linares
Author_Institution :
C3 y ICN, UNAM, M?xico D.F. 04510
fYear :
2015
fDate :
7/1/2015 12:00:00 AM
Firstpage :
1
Lastpage :
6
Abstract :
The Naive Bayes approximation and associated classifier is widely used in machine learning and data mining and offers very robust performance across a large spectrum of problem domains. As it depends on a very strong assumption - independence among features - this has been somewhat puzzling. Various hypotheses have been put forward to explain its success and moreover many generalizations have been proposed. In this paper we propose a set of "local" error measures - associated with the likelihood functions for particular subsets of attributes and for each class - and show explicitly how these local errors combine to give a "global" error associated to the full attribute set. By so doing we formulate a framework within which the phenomenon of error cancelation, or augmentation, can be quantitatively evaluated and its impact on classifier performance estimated and predicted a priori. These diagnostics also allow us to develop a deeper and more quantitative understanding of why the Naive Bayes approximation is so robust and under what circumstances one expects it to break down.
Keywords :
"Correlation","Robustness","Measurement uncertainty","Mathematical model","Electronic mail","Probability distribution","Data mining"
Publisher :
ieee
Conference_Titel :
Information, Intelligence, Systems and Applications (IISA), 2015 6th International Conference on
Type :
conf
DOI :
10.1109/IISA.2015.7388083
Filename :
7388083
Link To Document :
بازگشت