|
gptkbp:instanceOf
|
gptkb:model
classifier
|
|
gptkbp:advantage
|
fast training
simple implementation
works well with high-dimensional data
|
|
gptkbp:assumes
|
feature independence
|
|
gptkbp:basedOn
|
gptkb:Bayes'_theorem
|
|
gptkbp:category
|
supervised learning
probabilistic classifier
|
|
gptkbp:commonIn
|
information retrieval
natural language processing
diagnosis
|
|
gptkbp:featureType
|
binary
continuous
categorical
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Naive Bayes Classifier
|
|
gptkbp:implementedIn
|
gptkb:Weka
gptkb:scikit-learn
R
|
|
gptkbp:input
|
feature vector
|
|
gptkbp:introducedIn
|
1960s
|
|
gptkbp:limitation
|
not suitable for correlated features
strong independence assumption
|
|
gptkbp:mathematicalFormula
|
P(C|X) = P(X|C) * P(C) / P(X)
|
|
gptkbp:namedAfter
|
gptkb:Thomas_Bayes
|
|
gptkbp:openSource
|
gptkb:Weka
gptkb:scikit-learn
R
|
|
gptkbp:output
|
class label
|
|
gptkbp:performanceMetric
|
precision
F1 score
recall
accuracy
|
|
gptkbp:relatedTo
|
gptkb:Support_Vector_Machine
Logistic Regression
Decision Tree
|
|
gptkbp:trainingDataRequired
|
labeled data
|
|
gptkbp:usedFor
|
spam filtering
sentiment analysis
text classification
document categorization
|
|
gptkbp:uses
|
likelihood
posterior probability
prior probability
|
|
gptkbp:variant
|
gptkb:Bernoulli_Naive_Bayes
gptkb:Gaussian_Naive_Bayes
gptkb:Multinomial_Naive_Bayes
|
|
gptkbp:bfsParent
|
gptkb:Unigram_Language_Model
|
|
gptkbp:bfsLayer
|
8
|