Electrical Engineering Seminars

Architecting AI Systems for Deep Learning Recommendation and Beyond

Carole-Jean Wu, Research Scientist at Facebook AI Research

Mar 26, 2021

Please register here to attend the EE Seminars via Zoom this spring. Once you register, you will receive the Zoom link. You only need to register once to be able to attend any of the seminars. 


We witnessed a 300,000 times increase in the amount of compute for AI in the past decade. The latest natural language processing model is fueled with over trillion parameters while the memory need of neural recommendation and ranking models has grown from hundreds of gigabyte to the terabyte scale. This talk will introduce the underinvested deep learning personalization and recommendation systems in the overall system research community. The training of state-of-the-art industry-scale personalization and recommendation models consumes the highest number of compute cycles among all deep learning use cases at Facebook. For AI inference, recommendation use cases consume even higher compute cycles of 80%. What are the key system challenges faced by industry-scale neural personalization and recommendation models? This talk will highlight recent advances on AI system development for deep learning recommendation and the implications on infrastructure optimization opportunities across the machine learning system stack. System research for deep learning recommendation and AI at large is at a nascent stage. This talk will conclude with research directions for building and designing responsible AI systems – that is fair, efficient, and environmentally sustainable.  

Speaker Bio

Carole-Jean Wu is a Research Scientist at Facebook AI Research (on leave from ASU since 2018). Her research focus is in the domain of computer system architecture with particular emphasis on energy- and memory-efficient systems. Her work has pivoted into designing systems for machine learning execution at-scale, such as for personalized recommender systems and mobile deployment. In general, she is interested in tackling system challenges to enable efficient, responsible AI execution. Carole-Jean chairs the MLPerf Recommendation Benchmark Advisory Board, co-chaired MLPerf Inference, and serves on the MLCommons Board as a director. Carole-Jean received her M.A. and Ph.D. from Princeton and B.Sc. from Cornell. She is the recipient of the NSF CAREER Award, the IEEE Young Engineer of the Year Award, the Science Foundation Arizona Bisgrove Early Career Scholarship, among a number of Best Paper awards. 


David Brooks


Jessica Brenn