Overview
The upcoming workshop on Machine Learning and the Physical Sciences will take place at the 33rd Conference on Neural Information Processing Systems (NeurIPS) in December 2019. This event aims to unite experts from computer science, mathematics, and physical sciences to explore the intersection of machine learning and various physical challenges. The workshop is significant for advancing interdisciplinary dialogue and fostering innovative solutions to complex scientific problems.
Background & Relevance
Machine learning has proven to be a powerful tool in understanding and predicting complex phenomena across the physical sciences. From analyzing astronomical data to modeling quantum systems, the application of machine learning techniques is becoming increasingly vital. This workshop will address critical issues such as model interpretability and the integration of scientific knowledge into machine learning algorithms, which are essential for enhancing scientific discovery and understanding.
Key Details
- Event: Machine Learning and the Physical Sciences Workshop
- Date: December 13 or 14, 2019
- Location: Vancouver Convention Centre, Vancouver, BC, Canada
- Website: ml4physicalsciences.github.io
- Submission Deadline: September 9, 2019, 23:59 PDT
- Author Notification: October 1, 2019
- Camera-Ready Paper Deadline: November 1, 2019
Eligibility & Participation
This workshop invites contributions from researchers working on the application of machine learning in physical sciences. It targets both completed projects and high-quality works in progress, encouraging diverse submissions that can stimulate discussion and collaboration.
Submission or Application Guidelines
- Submissions should be anonymized short papers up to 4 pages in PDF format, following the NeurIPS style.
- References do not count towards the page limit.
- Appendices are discouraged, and reviewers will focus on the first 4 pages.
- All accepted papers will be presented as posters or talks during the workshop.
- Submissions will be peer-reviewed in a double-blind setting.
- For more details on submission, please check the workshop website for updates.
Additional Context / Real-World Relevance
The integration of machine learning with physical sciences is crucial for tackling some of the most pressing scientific challenges today. By leveraging machine learning techniques, researchers can enhance their understanding of complex systems, leading to breakthroughs in various fields such as climate science, particle physics, and beyond. This workshop represents an opportunity to bridge gaps between disciplines and promote innovative research.
Conclusion
Researchers and practitioners in the fields of machine learning and physical sciences are encouraged to participate in this workshop. This is a unique chance to present your work, engage with leading experts, and contribute to the evolving dialogue in this interdisciplinary area. For further information, please visit the workshop website and consider submitting your work.
Category: CFP & Deadlines
Tags: machine learning, physical sciences, neurips, generative models, model interpretability, variational inference, simulation-based models, experimental design
