Description

Frontiers of Foundation Models for Time Series

Discover the future of time series modeling with Yan Liu, PhD, as she explores the potential of GPT-inspired architectures for capturing dynamic patterns across diverse domains. In this talk, Professor Liu, a leading expert in machine learning at USC, discusses groundbreaking advancements in deep learning and their applications to time series, offering insights into how these innovations could transform fields like climate science, healthcare, and sustainability. Yan Liu brings her extensive expertise to this engaging session, sharing her perspective on the intersection of natural language processing and time series analysis. With accolades such as the NSF CAREER Award and leadership roles in top conferences like KDD and ICLR, her talk is a must-watch for anyone passionate about machine learning, AI, and cutting-edge research.

Instructors Bio

Yan Liu, PhD

Professor at University of Southern California

Yan Liu is a Professor in the Computer Science Department and the Director of the Machine Learning Center at the University of Southern California. She received her Ph.D. degree from Carnegie Mellon University. Her research interest is machine learning and its applications to climate science, health care, and sustainability. She has received several awards, including NSF CAREER Award, Okawa Foundation Research Award, New Voices of Academies of Science, Engineering, and Medicine, Best Paper Award in SIAM Data Mining Conference. She serves as general chair for KDD 2020 and ICLR 2023, and program chairs for WSDM 2018, SDM 2020, KDD 2022 and ICLR 2022.

Outline:

  • The AI Era: A Pivotal Moment

  • Fundamental AI - Pushing the Frontier of AI

  • Practical Challenges: Real-world Time Series Data

  • Foundation Models for Time Series | Contextual Information

  • Foundation Models for Spatiotemporal Data