Machine Learning Open Source Software

Open source tools have recently reached a level of maturity which makes them suitable for building large-scale real-world systems. At the same time, the field of machine learning has developed a large body of powerful learning algorithms for a wide range of applications.

JMLR is proud to support the open source movement by having a track on open source software in machine learning. The aim of this special section is to provide, in parallel to theoretical advances in machine learning, a venue for collection and dissemination of open source software. Furthermore, we believe that a resource of peer reviewed software accompanied by short articles would be highly valuable to the machine learning community in general, helping to build a common repository of machine learning software.

We encourage submissions which are contributions related to implementations of non-trivial machine learning algorithms, toolboxes or even languages for scientific computing. The software must adhere to a recognised open source license ( Evidence of an active user community should be demonstrated by, for example, listing the software on the mloss site. As with the main JMLR papers, all published papers are freely available online. Submissions should clearly indicate that they are intended for this special track in the cover letter of the submission.

Since we specifically want to honor the effort of turning a method into a highly usable piece of software, prior publication of the method is admissible, as long as the software has not been published elsewhere. If the software has been the main content of a paper appearing in a peer reviewed conference or journal, then there should be a document in the code repository (referred to in the cover letter of the submission), listing the software package's improvements and extensions. It is hoped that the open source track will motivate the machine learning community towards open science, where open access publishing, open data standards and open source software foster research progress.


We invite submissions of descriptions of high quality machine learning open source software implementations. Submissions should at least include:
  1. A cover letter stating that the submission is intended for the machine learning open source software section, the open source license the software is released under, the web address of the project, and the software version to be reviewed.
  2. An up to four page description based on the JMLR format, with a fifth page allowed for references only.
  3. A zip or compressed tar-archive file containing the source code and documentation.

Submission checklist

  1. Ensure the submitted code compiles and runs on all your supported platforms.
  2. Ensure the licensing terms of all included components comply with the open source definition and are clearly stated in the source package and mentioned in each source file.
  3. Ensure the source package contains no extra files, such as version control system files or '._' property files. (Remember that some of these may not be visible on your own platform.)

Review Criteria

The following guidelines would be used to review submissions. While ideally submissions should satisfy all the criteria below, they are not necessary requirements.
  1. The quality of the four page description.
  2. The novelty, breadth, and significance of the contribution (including evidence of an active user community).
  3. The openness of the project, such as a public source code repository, bug tracker, mailing list/forum, that allows new developers to participate and contribute.
  4. The clarity of design.
  5. The freedom of the code (lack of dependence on proprietary software).
  6. The breadth of platforms it can be used on (should include an open-source operating system).
  7. The quality of the user documentation (should enable new users to quickly apply the software to other problems, including a tutorial and several non-trivial examples of how the software can be used).
  8. The quality of the developer documentation (should enable easy modification and extension of the software, provide an API reference, provide unit testing routines).
  9. The quality of comparison to previous (if any) related implementations, w.r.t. run-time, memory requirements, features, to explain that significant progress has been made.

Accepted Papers

After acceptance, the abstract including the link to the software project website, the four page description and the reviewed version of the software will be published on the JMLR-MLOSS website The authors can then make sure that the software is appropriately maintained and that the link to the project website is kept up-to-date. When preparing this information, follow the JMLR instructions for formatting final sumbmissions. In addition to the LaTeX source, MLOSS authors must submit an single file containing an archive of the source code that will be published on the JMLR website. This file should be named according to the JMLR author conventions, for example jones03a-code.tar.gz.

Copyright ? JMLR 2007. All rights reserved.

Home Page





Editorial Board



Open Source Software



RSS Feed