You are viewing a preview of...

MTL: A Software Suite for Learning Related Tasks Simultaneously

Open-source software for multi-task learning that can improve generalised performance

Background

When analyzing a dataset, one must not only understand the relationship between the data points, but also the underlying structure of the set. The underlying structure of a dataset is generally estimated from the data on hand, leading to assumptions and less accurate predictions.

Technology Overview

In order to improve structure learning, Lawrence Livermore National Laboratory scientists have developed an open-source software suite called MTL. Multi-task learning (MTL) aims to improve generalization performance by learning multiple related tasks simultaneously. This software suite can handle any type of data and consists of multitask learning methods and a framework for easy experimentation with machine learning methods, leading to more accurate assumptions and predictions.

Further Details

MTL-suite, open-sourced software licensed under the

Log in or create a free account to continue reading