Skip to main content

Multi-Kernel Relevance Vector Machines

Bayesian classi?cation
algorithms, the multi-class multi-kernel Relevance Vector Ma-
chines (mRVMs) that have been recently proposed.

Since this is a multi-author blog and this is my first contribution, I will start by introducing myself. My name is Jason Marcell. I am a CS Masters student working under the supervision of Dr. Theodoros Damoulas. My primary work for Cornell’s ICS is a C++ implementation of two Bayesian classi?cation algorithms, the multi-class multi-kernel Relevance Vector Machines (mRVMs).

We are working openly on this project and its progress may be observed on github. The progress has been coming along slowly but steadily this past semester. Our initial goal so far has been to nail down all of the relevant operations required for implementing a classification machine model: reading user-supplied data from a file into a matrix, basic linear algebra operations, random sampling, etc. We have been using Google’s unit test framework for C++ to work slowly and carefully on small pieces of “building block” code that will later find its way into a proper, maintainable, object-oriented architecture. For our scientific math needs, we are using the GNU Scientific Library, a free and open-source library of routines that are of use to the scientific computing community.

More to come as progress is made!

Note: I had originally begun blogging over here, but all subsequent posts will live over here from now on.


Leave a Reply


Recent Comments

    Skip to toolbar