k-NN

GPTKB entity

Statements (49)
Predicate Object
gptkbp:instanceOf gptkb:algorithm
gptkbp:advantage simple to implement
no training phase
sensitive to irrelevant features
sensitive to the scale of data
computationally expensive at prediction time
gptkbp:alternativeName k nearest neighbor
k-nearest neighbour
kNN
kNN classifier
gptkbp:application bioinformatics
image recognition
recommender systems
anomaly detection
text categorization
gptkbp:canBe binary classification
multiclass classification
multi-label classification
gptkbp:category instance-based learning
lazy learning
gptkbp:commonLibrary gptkb:Weka
gptkb:scikit-learn
gptkb:MLlib
gptkbp:field gptkb:machine_learning
pattern recognition
gptkbp:fullName k-nearest neighbors
gptkbp:hasConcept classifies a sample based on the majority label among its k nearest neighbors
https://www.w3.org/2000/01/rdf-schema#label k-NN
gptkbp:hyperparameter k (number of neighbors)
gptkbp:introduced gptkb:Evelyn_Fix
Joseph Hodges
gptkbp:introducedIn 1951
gptkbp:measures gptkb:Hamming_distance
gptkb:Manhattan_distance
gptkb:Minkowski_distance
Euclidean distance
gptkbp:output class label
regression value
gptkbp:requires feature scaling
gptkbp:supportsAlgorithm nearest centroid classifier
radius neighbors classifier
weighted k-NN
gptkbp:type supervised learning
non-parametric method
gptkbp:usedFor gptkb:dictionary
regression
gptkbp:bfsParent gptkb:OpenSearch_Plugins
gptkb:KNN_(K-Nearest_Neighbors)
gptkbp:bfsLayer 8