Description:

Simple and hopefully clean and easy to follow implementation of the Generalized Learning Vector Quantizer (GLVQ) - a prototype based classifier originally proposed by Sato & Yamada. I provide the code with variants for metric adaptation (RGLVQ, GMLVQ, LiRaM).

The implementation makes some simplifications and is compositional (e.g. the used metric is a matlab class and not directly implemented in the algorithm). I also use the minFunc toolbox to avoid any direct dependency to the used optimization scheme. Hence the code has much fewer parameters as you will typically find for GLVQ code.

The archive comes with a small demo script showing a typical run for with the different GLVQ variants.

Changes to previous version:

Initial Announcement on mloss.org.

BibTeX Entry: Download

Corresponding Paper BibTeX Entry: Download

Supported Operating Systems: Platform Independent

Data Formats: Any Format Supported By Matlab

Tags: Classification, Glvq, Liram, Relevance Learning

Archive: download here

Comments

No one has posted any comments yet. Perhaps you'd like to be the first?

Leave a comment

You must be logged in to post comments.