- From Learning, to Meta-Lear...
- Edit Event
- Cancel Event
- Preview Reminder
- Send Reminder
- Other events happening in May 2022
From Learning, to Meta-Learning, to "Lego-Learning” – theory, system, and engineering
, Mohamed bin Zayed University of Artificial Intelligence
Date: Monday, May 09, 2022
Time: 3:30 PM to 5:00 PM Note: all times are in the Eastern Time Zone
Location: https://mit.zoom.us/j/94131305204, Patil/Kiva Seminar Room (G449)
Event Type: Seminar
Host: Manolis Kellis
Contact: Jeffrey Taft, firstname.lastname@example.org
Speaker URL: None
TALK: From Learning, to Meta-Learning, to "Lego-Learning” – theory, system, and engineering
Software systems for complex tasks - such as controlling manufacturing processes in real-time; or writing radiological case reports within a clinical workflow – are becoming increasingly sophisticated and consist of a large number of data, model, algorithm, and system elements and modules. Traditional benchmark/leaderboard-driven bespoke approaches in the Machine Learning community are not suited to meet the highly demanding industrial standards beyond algorithmic performance, such as cost-effectiveness, safety, scalability, and automatability, typically expected in production systems. In this talk, I discuss some technical issues toward addressing these challenges: 1) a theoretical framework for panoramic learning with all experiences; 2) optimization methods to best the effort for learning under such a principled framework; 3) compositional strategies for building production-grade ML programs from standard parts. I will present our recent work toward developing a standard model for Learning that unifies different special-purpose machine learning paradigms and algorithms, then a Bayesian blackbox optimization approach to Meta Learning in the space of hyperparameters, model architectures, and system configurations, and finally principles and designs of standardized software Legos that facilitate cost-effective building, training, and tunning of practical ML pipelines and systems.
Created by Jeffrey Taft at Friday, May 06, 2022 at 2:25 PM.