Link to the University of Pittsburgh Homepage
Link to the University Library System Homepage Link to the Contact Us Form

Physics-guided Machine Learning for Scientific Knowledge Discovery

Jia, Xiaowei (2021) Physics-guided Machine Learning for Scientific Knowledge Discovery. In: Pitt Momentum Fund 2021.

[img]
Preview
PDF (Showcase Poster)
Download (491kB) | Preview

Abstract

Machine learning (ML) has found immense success in commercial applications such as computer vision and natural language processing. Given the success of ML in commercial domains, there is an increasing interest in using ML models for advancing scientific discovery. However, direct application of ``black-box" ML models has met with limited success in scientific domains given that the data available for many scientific problems is far smaller than what is needed to effectively train advanced ML models. Additional challenge arises due to the data non-stationarity in space and time. In the absence of adequate information about the physical mechanisms of real-world processes, ML approaches are prone to false discoveries of patterns which look deceptively good on training data but cannot generalize to unseen scenarios.


Share

Citation/Export:
Social Networking:
Share |

Details

Item Type: Conference or Workshop Item (Poster)
Creators/Authors:
CreatorsEmailPitt UsernameORCID
Jia, XiaoweiXIAOWEI@pitt.eduxiaowei0000-0001-8544-5233
Centers: Other Centers, Institutes, Offices, or Units > Office of Sponsored Research > Pitt Momentum Fund
Date: 2021
Event Title: Pitt Momentum Fund 2021
Event Type: Other
DOI or Unique Handle: 10.18117/gvwj-3q81
Schools and Programs: School of Computing and Information > Computer Science
Refereed: No
Date Deposited: 26 Mar 2021 19:09
Last Modified: 26 Mar 2021 19:09
URI: http://d-scholarship.pitt.edu/id/eprint/40348

Metrics

Monthly Views for the past 3 years

Plum Analytics

Altmetric.com


Actions (login required)

View Item View Item