h2oEnsemble R Package
Permalink: 2015-11-22 23:30:00-08:00
by admin
in Software
tags: R ensemble learning machine learning
The h2oEnsemble R package provides functionality to create ensembles from the base learning algorithms that are accessible via the h2o R package (H2O version 3.0 and above). The H2O machine learning software features distributed implementations of many popular machine learning methods that can be run on a local machine or a cluster.
This type of ensemble learning is called "super learning", "stacked regression" or "stacking." The Super Learner algorithm learns the optimal combination of the base learner fits. In a 2007 article titled, "Super Learner", it was shown that the super learner ensemble represents an asymptotically optimal system for learning.
A tutorial for the h2oEnsemble package is available here.
Author(s): Erin LeDell