| |
Lecture Series In AI
|
| With Richard Zemel (Prof. Engg & Applied Science In CS, Columbia). |
| Columbia School of Engg, To Be Announced |
|
Mar 27 (Fri) , 2026 @ 10:30 AM
| |
FREE |
|
|
|
|
|
|
|
|
| |
| DETAILS |
|
Schedule:
10:30-11:00am Check-in
11:00-12:00pm Lecture
Advance registration required for both Columbia non-affiliates & Columbia affiliates.
About the Speaker
Richard Zemel is the Trianthe Dakolias Professor of Engineering & Applied Science in the Computer Science Department at Columbia University. He is the Director of the NSF AI Institute for Artificial & Natural Intelligence (ARNI), & was the co-founder & inaugural Research Director of the Vector Institute for Artificial Intelligence. His awards include an AI Lifetime Achievement Award (CAIA) & a Pioneer of AI Award (NVIDIA). His research contributions include foundational work on systems that learn useful representations of data with little or no supervision; graph-based machine learning; & algorithms for fair & robust machine learning.
About the Lecture
"Integrating Past & Present in Continual Learning"
Continual learning aims to bridge the gap between typical human & machine-learning environments. The continual setting does not have separate training & testing phases, & instead models are evaluated online while learning novel concepts & tasks. The most capable current AI systems struggle to learn new knowledge sequentially without forgetting old ones. Challenging research questions include how to rapidly assess a learner system's abilities & how to most efficiently train it to improve on a sequence of tasks. I will describe recent progress on these questions, across various research groups in ARNI, our NSF AI Institute for Artificial & Natural Intelligence. Finally we will consider open issues & challenges in continual learning.
Campus Access
In accordance with the University's current visitor guidelines, all non-Columbia guests will receive a QR code within a few hours of the event date. The code will be sent to you via email from CU Guest Access & must be presented for campus entry, along with a government-issued ID.
Accessibility
Columbia University makes every effort to accommodate individuals with disabilities. If you require disability accommodations to attend an event at Columbia University, please contact the Office of Disability Services at 212.854.2388 or access@columbia.edu.
Photography/Videography
Columbia Engineering reserves the right to capture & use images (including video, photo, audio) of student participants at this event in its current or future marketing materials. These materials include but are not limited to: social media, digital and/or print posters, email & web-based materials. By attending & participating in this event, you are consenting to having your image captured for these purposes. If you have concerns about your likeness being used, please reach out to engineeringcommunications@columbia.edu & we will accommodate your request.
|
|
|
|
|
|
|
|
