|
|
| |
EVENT DETAILS |
The Machine Learning New York City (ML-NYC) Speaker Series & Happy Hour is a monthly event for machine learning practitioners, researchers, & students to meet & watch talks from leading researchers in the field. Each event will feature a New York City-based speaker presenting their work, followed by a reception. The ML-NYC Speaker Series is open to anyone interested in machine learning research, & we encourage everyone to attend, whether you are just getting started in research or an expert in the field.
We are excited to welcome Shirley Ho as our next speaker on Thursday, Feburary 22. The talk will begin at 4pm at the Flatiron Institute, followed by a reception. You must register on Eventbrite to attend the talk & reception.
Title: Foundation Models for Science (Or Can we build a scienceGPT)?
Abstract: In recent years, the fields of natural language processing & computer vision have been revolutionized by the success of large models pretrained with task-agnostic objectives on massive, diverse datasets. This has, in part, been driven by the use of self-supervised pretraining methods which allow models to utilize far more training data than would be accessible with supervised training. These so-called ``foundation models have enabled transfer learning on entirely new scales. Despite their task-agnostic pretraining, the features they extract have been leveraged as a basis for task-specific finetuning, outperforming supervised training alone across numerous problems especially for transfer to settings that are insufficiently data-rich to train large models from scratch. In this talk, I will show preliminary results from our team Polymathic AI on applying this approach to a variety of scientific problems & speculate what are possible future directions.
Bio: Shirley Ho is a senior research scientist at CCA & she joined the Foundation in 2018 to lead the Cosmology X Data Science group. Her research interests range from cosmology to developing new machine learning methods for scientific data that leverage shared concepts across scientific domains.
Ho has extensive expertise in astrophysical theory, observation, & data science. She focuses on novel statistical & machine learning tools to address cosmic mysteries like the origins & fate of the universe.
Ho analyzes data from surveys including ACT, Euclid, LSST, Simons Observatory, SDSS, & Roman Space Telescope to understand our universe's evolution. She earned her Ph.D. in Astrophysical Sciences from Princeton in 2008 & B.S. degrees in Computer Science & Physics from UC Berkeley in 2004.
Ho was previously a Chamberlain & Seaborg Fellow at Lawrence Berkeley National Lab. She joined Carnegie Mellon as an Assistant Professor in 2011, becoming Cooper Siegel Career Development Chair Professor & tenured Associate Professor. In 2016 she moved to Lawrence Berkeley Lab as a Senior Scientist.
Since 2011, Ho has mentored over 50 postdocs, 10 Ph.D. students, & 20 undergraduates in astrophysics, computer science, & statistics. Her awards include the Macronix Prize, Carnegie Science Award, Blavatnik National Finalist, & the EPS Giuseppe & Vanna Cocconi Prize in Cosmology.
Organizers: The ML-NYC Speaker Series is organized by professors David Blei, Joan Bruna, & Lawrence Saul, Flatiron Fellows Neha Wadia & Brett Larsen, & PhD student Claudia Shi & Noah Amsel. Please email nycmachinelearning@gmail.com if you have any questions. You can also follow us on Twitter @MLNYCSeries, join our mailing list, or check out our website.
Protocols:
- By entering the building each person implicitly attests that they do not have symptoms consistent with COVID & they are not knowingly COVID positive.
- Enter with a government issued ID (you will need to show your ID, not the QR code from Eventbrite) when arriving at the building.
- There is NO food or drink allowed in the auditorium.
- Please do not arrive earlier than 30 minutes before the event.
The Flatiron Institute is located at 162 Fifth Ave. The entrance is on 21st street between 5 & 6 Ave & the IDA auditorium is located on the 2nd floor.
|
|
|
|
|
|