Professor Jason Hattrick-Simpers
Department of Material Science & Engineering
University of Toronto
Abstract:
The past few years have been marked by a literal exponential increase in the number of publications with the words “machine learning,” “artificial intelligence,” and “deep learning” in their titles. These tools now pervade materials science workflows and have been integrated with experimental/computational automation to form autonomous research agents, capable of planning, executing, and analyzing entire scientific campaigns. Lurking beneath the surface truly amazing accomplishments are serious questions around trust, bias, reproducibility, and equity which will ultimately determine the overall adoption of AI and autonomy by the broader community. Here, I will speak to recent work done by our group to systematically (1) remove human bias from experimental data analysis, (2) identify and actively remediate bias in large datasets , and (3) foster and promote a community of equity and reproducibility within the materials AI sub-domain. Specific case studies will center around standard electrochemical impedance spectroscopy analysis, building stability model predictions for complex alloys from large theoretical datasets, and maximizing the amount of information extracted from imaging techniques.
Bio:
Jason Hattrick-Simpers is a Professor in the Department of Materials Science and Engineering, University of Toronto, and a Research Scientist at CanmetMATERIALS. He graduated with a B.S. in Mathematics and a B.S. in Physics from Rowan University and a Ph.D. in Materials Science and Engineering from the University of Maryland. His research interests focus on using AI and experimental automation to discover new functional alloys and oxides that can survive in extreme environments and materials for energy conversion and storage.
Microsoft Teams meeting:
Join on your computer, mobile app or room device
Click here to join the meeting
Meeting ID: 296 827 043 532
Passcode: mRNTRW
Download Teams | Join on the web
Or call in (audio only)
+1 647-794-1609,,176390674# Canada, Toronto
Phone Conference ID: 176 390 674#