Glossary term
Glossary term
Foundations
A classification algorithm that seeks to maximize the margin between positive and negative classes by mapping input data vectors to a higher dimensional space. For example, consider a classification problem in which the input dataset has a hundred features. To maximize the margin between positive and negative classes, a KSVM could internally map those features into a million-dimension space. KSVMs uses a loss function called hinge loss.
Created for this library
A research team uses Kernel Support Vector Machines as a strong baseline on a small structured dataset before evaluating neural models.
A small medical analytics team uses Kernel Support Vector Machines on tabular data where modern deep models add cost without much gain.
A bioinformatics team uses Kernel Support Vector Machines with a custom kernel to classify protein sequences in a moderate-size dataset.
Definition source: Google for Developers Machine Learning Glossary | Creative Commons Attribution 4.0 License