Oger: Modular Learning Architectures for Large-Scale Sequential Processing
Abstract
Oger (OrGanic Environment for Reservoir computing) is a Python toolbox for building, training and evaluating modular learning architectures on large data sets. It builds on MDP for its modularity, and adds processing of sequential data sets, gradient descent training, several cross-validation schemes and parallel parameter optimization methods. Additionally, several learning algorithms are implemented, such as different reservoir implementations (both sigmoid and spiking), ridge regression, conditional restricted Boltzmann machine (CRBM) and others, including GPU accelerated versions. Oger is released under the GNU LGPL, and is available from http://organic.elis.ugent.be/oger.
Cite
Text
Verstraeten et al. "Oger: Modular Learning Architectures for Large-Scale Sequential Processing." Machine Learning Open Source Software, 2012.Markdown
[Verstraeten et al. "Oger: Modular Learning Architectures for Large-Scale Sequential Processing." Machine Learning Open Source Software, 2012.](https://mlanthology.org/mloss/2012/verstraeten2012jmlr-oger/)BibTeX
@article{verstraeten2012jmlr-oger,
title = {{Oger: Modular Learning Architectures for Large-Scale Sequential Processing}},
author = {Verstraeten, David and Schrauwen, Benjamin and Dieleman, Sander and Brakel, Philemon and Buteneers, Pieter and Pecevski, Dejan},
journal = {Machine Learning Open Source Software},
year = {2012},
pages = {2995-2998},
volume = {13},
url = {https://mlanthology.org/mloss/2012/verstraeten2012jmlr-oger/}
}