Deep State Space Models for Sequence Modeling
This talk will cover recent deep neural networks based on state space models (SSM) based from S4. I'll go over the core properties and mechanics of SSMs, and discuss the key features of S4 and variants. I'll also focus on discussing the relationship of SSMs with established deep learning models (RNNs, CNNs, Attention) and their corresponding strengths and weaknesses, including potential application areas and promising directions.
Albert is an incoming Assistant Professor of Machine Learning at Carnegie Mellon University. His research focuses on theoretical approaches for modeling sequences with deep learning, and algorithms for computational primitives such as structured matrix operations. He completed his PhD at Stanford University under the supervision of Christopher Ré, and is currently working at DeepMind during a gap year.
To become a member of the Rough Path Interest Group, register here for free.