Tutorial of Active Learning Algorithms for Deep Learning смотреть онлайн

In this video, we discuss what active learning is and various active learning strategies present in DISTIL. We present a discussion on active learning strategies namely, Uncertainty Sampling, Coreset, FASS, BADGE, GLISTER-ACTIVE, Adversarial Techniques and BALD. For each of these strategies we present the underlying idea and try to differentiate them from one another.

Read more at https://decile-research.medium.com/active-learning-strategies-distil-62ee9fc166f9


-----------------------
DISTIL is a library that features many state-of-the-art active learning algorithms. Implemented in PyTorch, it gives fast and efficient implementations of these active learning algorithms. It allows users to modularly insert active learning selection into their pre-existing training loops with minimal changes. Most importantly, it features promising results in achieving high model performance with less amount of labeled data. If you are looking to cut down on labeling costs, DISTIL should be your go-to for getting the most out of your data.


Visit our webpage or github profile to checkout our other useful pytorch libraries

Note: If you face any issue while trying out the DISTIL library in your project, please do raise an issue in github

-- Stay in Touch --

Webpage: https://decile.org/
Blog: https://medium.com/@decile-research
Github: https://github.com/decile-team/distil
Twitter: https://twitter.com/decile_research
Linkedin: https://www.linkedin.com/in/decile