Numerical Mathematics Challenges in Machine Learning
By inviting numerical mathematics researchers with interest in both numerical methodology and real problems in applications close to machine learning, we probe realistic routes out of the prototyping sandbox. Our aim is to strengthen dialog between NM, signal processing, and ML. Speakers are briefed to provide specific high-level examples of interest to ML and to point out accessible software. We initiate discussions about how to best bridge gaps between ML requirements and NM interfaces and terminology.
The workshop reinforces the community’s awakening attention towards critical issues of numerical scalability and robustness in algorithm design and implementation. Further progress on most real-world ML problems is conditional on good numerical practices, understanding basic robustness and reliability issues, and a wider, more informed integration of good numerical software. As most real-world applications come with reliability and scalability requirements that are by and large ignored by most current ML methodology, the impact of pointing out tractable ways for improvement is substantial.
Workshop homepage: http://numml.kyb.tuebingen.mpg.de/
Reviews and comments:
Thanks for sharing this post! The mission of this workshop was to understand how machine learning(ML)problems can be solved by numerical software! A clear explanation of this numerical mathematics could find a way to real this ML learning process. I also want to recommend this https://plainmath.net/ source to help students with mathematics video tutorials. The workshop organizers did an excellent job and I hope they will arrange some programs periodically!
Write your own review or comment: