NASA Logo, National Aeronautics and Space Administration

+NASA Home

+Ames Home

Hamed Valizadegan To Give Invited Talk at Machine Learning Innovation Summit
Intelligent Systems Division Banner

Hamed Valizadegan To Give Invited Talk at Machine Learning Innovation Summit

Hamed Valizadegan will give an invited talk entitled “Machine Learning for Space Research Problems” at the Machine Learning Innovation Summit in San Francisco on June 8th. The talk will present team-member efforts in developing and applying machine learning techniques to (1) predict the lifetime of Fine-Guidance Sensors (FGSs) in the Hubble Space Telescope using sensor data, and (2) automatically classify Kepler Mission transit signals for exoplanet detection. These two case studies will be utilized to demonstrate challenges and solutions in applying machine-learning techniques to space problems. The first challenge deals with extremely small sample size. In the case of FGS lifetime prediction, there are only six FGSs (three of which have failed). The talk will demonstrate how domain knowledge can be used to design novel machine-learning solutions to overcome the data scarcity problem. The second challenge deals with extremely large sample size (e.g., a huge number of stars to monitor for exoplanet transit signals), but with only a small amount of labeled data and limited domain knowledge. The talk will discuss how the abundant data availability can help to compensate for limited labeled data and domain knowledge.

BACKGROUND: The Machine Learning Innovation Summit is a two-day event being held in San Francisco June 8-9 (Machine Learning Innovation Summit). The summit features over 20 invited talks from influential data scientists from industry and government, with more than 100 data science & analytics industry leaders in attendance. Speakers represent Uber, eBay, Walmart, Netflix, LinkedIn, Mercedes-Benz USA, Kohl’s, Yahoo, Twitter, and Hotels.com, among others. The event shares best practices and thoughts on the future of machine learning from a wide spectrum of enterprises.

The Data Sciences Group in the Intelligent Systems Division is a collaboration of scientists in a variety of fields, including Integrated System Health Management, Aeronautics, Space Exploration, and Earth and Space Sciences. The group conducts fundamental research to create tools and methods that answer pressing scientific questions in the fields of machine learning, knowledge discovery, and other areas, as well as aid in the assimilation and understanding of scientific and engineering data to best advance NASA's missions.

NASA PROGRAM FUNDING: NASA Engineering and Safety Center

TEAM: TI: Rodney Martin, Bryan Matthews, Nikunj Oza, and Hamed Valizadegan; Engineering Systems Division (RE): Jon Jenkins; National Aeronautics Research Institute (NARI): Koushik Datta

POINT OF CONTACT: Hamed Valizadegan, hamed.valizadegan@nasa.gov

First Gov logo
NASA Logo - nasa.gov