Skip to content

Multi task learning

Toby Dylan Hocking edited this page May 9, 2017 · 1 revision

Background

The MALSAR package implements several methods for multi-task learning, but is only available for MATLAB.

Related work

TODO: discuss other R packages that implement methods for multi-task learning. glmnet?

Details of your coding project

  • Convert the MATLAB code to an R package. TODO: details about which functions we want to focus on?

Expected impact

The R community will for the first time be able to solve a variety of multi-task learning problems.

Mentors

Ideally this project should have one mentor who is familiar with the original MALSAR code, and another who is an expert R package developer. If there are any interested students, please try to email the MALSAR authors, and ask if they can mentor. If they can, TD Hocking <[email protected]> could be the R co-mentor. Sir Jiayu Zhou won’t consider to mentor students for this project who are not from MSU. Kindly don’t contact and ask him for the same.

Tests

TODO Several tests that potential students can do to demonstrate their capabilities for this particular project. Please modify the suggestions below to make them specific for your project.

  • Easy: something that any useR should be able to do, e.g. download some existing package listed in the Related Work, and run it on some example data.
  • Medium: something a bit more complicated. You can encourage students to write a script or some functions that show their R coding abilities.
  • Hard: Can the student write a package with Rd files, tests, and vigettes? If your package interfaces with non-R code, can the student write in that other language?

Solutions of tests

Students, please post a link to your test results here.

Clone this wiki locally