The mysterious optimality of Naive Bayes: Estimation of the probability in the system of "classifiers"

O. Kupervasser

doi:https://doi.org/10.1134/S1054661814010088

The mysterious optimality of Naive Bayes: Estimation of the probability in the system of "classifiers"

Research output: Contribution to journal › Article › peer-review

Abstract

Bayes Classifiers are widely used currently for recognition, identification and knowledge discovery. The fields of application are, for example, image processing, medicine, chemistry (QSAR). However, by mysterious way the Naive Bayes Classifier usually gives a very nice and good presentation of recognition. More complex models of Bayes Classifier cannot improve it considerably. We demonstrate here a very nice and simple proof of the Naive Bayes Classifier optimality that can explain this interesting fact. The derivation in the current paper is based on a paper of the author written in 2002.

Original language	English
Pages (from-to)	1-10
Number of pages	10
Journal	Pattern Recognition and Image Analysis
Volume	24
Issue number	1
DOIs	https://doi.org/10.1134/S1054661814010088
State	Published - Jan 2014
Externally published	Yes

Keywords

Bayes Classifier
Naive Bayes
QSAR
optimality
recognition

All Science Journal Classification (ASJC) codes

Computer Vision and Pattern Recognition
Computer Graphics and Computer-Aided Design

Access to Document

https://doi.org/10.1134/S1054661814010088

Cite this

@article{9634ec801dfb4b5fb9276bea6e994874,

title = "The mysterious optimality of Naive Bayes: Estimation of the probability in the system of {"}classifiers{"}",

abstract = "Bayes Classifiers are widely used currently for recognition, identification and knowledge discovery. The fields of application are, for example, image processing, medicine, chemistry (QSAR). However, by mysterious way the Naive Bayes Classifier usually gives a very nice and good presentation of recognition. More complex models of Bayes Classifier cannot improve it considerably. We demonstrate here a very nice and simple proof of the Naive Bayes Classifier optimality that can explain this interesting fact. The derivation in the current paper is based on a paper of the author written in 2002.",

keywords = "Bayes Classifier, Naive Bayes, QSAR, optimality, recognition",

author = "O. Kupervasser",

year = "2014",

month = jan,

doi = "https://doi.org/10.1134/S1054661814010088",

language = "الإنجليزيّة",

volume = "24",

pages = "1--10",

journal = "Pattern Recognition and Image Analysis",

issn = "1054-6618",

publisher = "Pleiades Publishing",

number = "1",

}

TY - JOUR

T1 - The mysterious optimality of Naive Bayes

T2 - Estimation of the probability in the system of "classifiers"

AU - Kupervasser, O.

PY - 2014/1

Y1 - 2014/1

N2 - Bayes Classifiers are widely used currently for recognition, identification and knowledge discovery. The fields of application are, for example, image processing, medicine, chemistry (QSAR). However, by mysterious way the Naive Bayes Classifier usually gives a very nice and good presentation of recognition. More complex models of Bayes Classifier cannot improve it considerably. We demonstrate here a very nice and simple proof of the Naive Bayes Classifier optimality that can explain this interesting fact. The derivation in the current paper is based on a paper of the author written in 2002.

AB - Bayes Classifiers are widely used currently for recognition, identification and knowledge discovery. The fields of application are, for example, image processing, medicine, chemistry (QSAR). However, by mysterious way the Naive Bayes Classifier usually gives a very nice and good presentation of recognition. More complex models of Bayes Classifier cannot improve it considerably. We demonstrate here a very nice and simple proof of the Naive Bayes Classifier optimality that can explain this interesting fact. The derivation in the current paper is based on a paper of the author written in 2002.

KW - Bayes Classifier

KW - Naive Bayes

KW - QSAR

KW - optimality

KW - recognition

UR - http://www.scopus.com/inward/record.url?scp=84897435498&partnerID=8YFLogxK

U2 - https://doi.org/10.1134/S1054661814010088

DO - https://doi.org/10.1134/S1054661814010088

M3 - مقالة

SN - 1054-6618

VL - 24

SP - 1

EP - 10

JO - Pattern Recognition and Image Analysis

JF - Pattern Recognition and Image Analysis

IS - 1

ER -

The mysterious optimality of Naive Bayes: Estimation of the probability in the system of "classifiers"

Abstract

Keywords

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this