Machine Learning
267 views
Kernel Trick
Quick Definition
Transforming data to higher dimensions for linear separability
Full Definition
A technique transforming data into higher dimensions to make it linearly separable without explicit transformation.
Examples
SVM non-linear classification, kernel PCA, RBF kernel
Related Terms
support-vector-machine
dimensionality-reduction
More Machine Learning Terms
Confusion Matrix
Table visualizing classifier performance by class predictions
CatBoost
Gradient boosting library with native categorical feature support
Supervised Learning
Learning from labeled training data with input-output pairs
Gaussian Mixture Model
Probabilistic model using multiple Gaussian distributions
PCA
Statistical technique reducing dimensionality via principal components
Feature Engineering
Creating and transforming input variables to improve performance