Home / Curated / Preprocessing Methods

Preprocessing Methods

4 Concepts

Feature engineering, data augmentation, and tokenization procedures.

Showing 4 of 4

Concept	Origin	Kind / Branch	Identifier	Evidence / Status
Cutout A training-image augmentation method that removes information from a randomly located square region by replacing that region with zeros in t…	Curated	Preprocessing Methods	`AIMech:Cutout`	1 claim 1 source
RAPID support vector data description sampling aka RAPID, Reducing samples by pruning of inlier densities A density-based training-subset selection method for support vector data description that prefilters low-density observations and greedily r…	Curated	Preprocessing Methods	`AIMech:RapidSupportVectorDataDescriptionSampling`	8 claims 5 sources
SMOTE-NC The original mixed nominal/continuous extension of SMOTE that synthesizes minority-class training examples by finding minority neighbors wit…	Curated	Preprocessing Methods	`AIMech:SMOTENC`	6 claims 1 source
Synthetic Minority Over-sampling Technique aka SMOTE A minority-class oversampling method that generates synthetic labeled feature vectors by interpolating between an observed minority example…	Curated	Preprocessing Methods	`AIMech:SyntheticMinorityOversamplingTechnique`	1 claim 1 source