SUL Topic 4 - SVM Flashcards
Support Vector Machines (SVM)
Classification technique for predicting binary outcomes using labelled and balanced datasets
Black box technique
Characteristic of SVM where individual variable influence cannot be determined
Hyperplane
What SVM learns to classify data into two classes
Kernel Trick
Method used to transfer input space to feature space when data points are not linearly separable
Kernel function
Maps pairs of data points onto their inner products and transforms data from lower to higher dimensions
Max-margin hyperplane
Result of mathematical minimization in feature space, identifying non-linear boundary in original data space
Support vectors
Extreme data points that SVM focuses on for precise classification
Linear and non-linear separable data
Types of datasets SVM can handle using kernel functions
High feature-to-sample ratios
A challenge faced by SVM requiring careful parameter tuning
SVM applications
Fields including medical imaging
Financial predictions
Pattern recognition
Categorical attribute handling in SVM
Convert categorical values to numeric values
Multi-class SVM
Combines two-class SVMs to handle non-binary classification
Training time for SVM
May be very long for large-scale problems
Accuracy Measure
Classification measure used to evaluate SVM performance
Confusion Matrix
Tool used to assess SVM classification results