You are here

Cloud-scale, Flexible Scaling and Factoring of Machine Learning Algorithms: The FlexGP Project

 

In a nutshell, the FlexGP project goal is scalable machine learning using genetic programming (GP).  Genetic programming is a mature, robust multi-point search technique (inspired by evolution) which supports readable, and flexibly specified learning representations which can readily express linear or non-linear data relationships. It is well suited to parallelization and machine learning. It has a strong record in real world domains.

Learn more FlexGP project:  http://flexgp.csail.mit.edu/index.php

The project offers multiple open source releases.:

 * */Evolutionary learners:/* this layer provides access to the learners
   so that one could run them on their desktop. See description of the
   learners here <http://flexgp.github.io/gp-learners/> and a tutorial to
   running them on multiple examples here
   <http://flexgp.github.io/gp-learners/blog.html>

 * */FlexGP: <http://flexgp.github.io/flexgp/>/* a cloud based platform
   for generating transparent non-linear large scale regression problems

 * */FCUBE: <http://flexgp.github.io/FCUBE/>/* A data parallel approach to
   building ensemble of classifiers

 

Investigators: