AI Center x CLAIRE - ML Fundamentals seminar - Prof. Albert Gu

The talk is jointly organized by the EPFL AI Center and the CLAIRE Lab. 

The talk will be followed by a coffee session. 

For on-site logistics, please use the following form to register: registration form.

Title
Structured State Space Models for Deep Sequence Modeling

Abstract
Substantial recent progress in machine learning and artificial intelligence has been driven by advances in sequence models, which form the backbone of deep learning models that have achieved widespread success across scientific applications. However, existing methods still have many drawbacks, including computational inefficiency and difficulty modeling more complex sequential data, such as when long sequences are involved. As such, it remains of fundamental importance to continue to develop principled and practical methods for modeling sequences. This talk provides an overview of structured state space models (SSMs), a recent approach to deep sequence modeling that is theoretically grounded, computationally efficient, and achieves strong results across a variety of data modalities and applications.

Bio
Prof. Albert Gu is assistant Professor in the Machine Learning Department at Carnegie Mellon University. His research broadly studies structured representations for advancing the capabilities of machine learning and deep learning models, with focuses on structured linear algebra, non-Euclidean representations, and theory of sequence models. Previously, he completed a Ph.D in the Department of Computer Science at Stanford University, advised by Christopher Ré and completed a B.S. in Mathematics and Computer Science at Carnegie Mellon University, and an internship at DeepMind.