Multi-task Learning (MTL) is a collection of techniques intended to learn multiple tasks simultaneously instead of learning them separately. The motivation behind MTL is to create a “Generalist” model that can solve multiple tasks rather than creating multiple “Specialist” models that are trained to solve only one task. Specifically, MTL improves generalization by leveraging the information contained in the training signals of related tasks. In this article series, we’ll do an in-depth study on MTL, starting with the basics and gradually transitioning to the popular approaches in the MTL literature. This series is self-contained and expects familiarity with the basics of Machine Learning. This is Part 1 of the series and sets up the foundation for getting started with MTL.
Outline Part 1:
- What is a TASK?
- The motivation behind Multi-task Learning
- Differentiating various Learning Paradigms
- Examples of Multi-task Learning
- Major Challenges in Multi-task Learning
Part 2 of this article series is now available here.
#multitask-learning #machine-learning #nlp #deep-learning
