What is it about?
CurML is the first curriculum machine learning library to integrate existing curriculum learning algorithms into a unified framework. It is convenient to use and flexible to customize by calling the provided five APIs, which are designed for easily plugging into a general training process and conducting the data-oriented, model-oriented and loss-oriented curricula.
Featured Image
Photo by Tim Mossholder on Unsplash
Why is it important?
CurML helps the researchers to reproduce, compare, evaluate and choose curriculum learning algorithms. It is open source, convenient to run, flexible to combine and extend, and easy to apply and plug in.
Perspectives
We hope this library can promote the development and application of curriculum learning.
Yuwei Zhou
Tsinghua University
Read the Original
This page is a summary of: CurML: A Curriculum Machine Learning Library, October 2022, ACM (Association for Computing Machinery),
DOI: 10.1145/3503161.3548549.
You can read the full text:
Contributors
The following have contributed to this page
