Skip to yearly menu bar Skip to main content


Poster

Continuous Spatiotemporal Transformer

Antonio Henrique de Oliveira Fonseca · Emanuele Zappala · Josue Ortega Caro · David van Dijk

Exhibit Hall 1 #419
[ ]
[ PDF [ Poster

Abstract:

Modeling spatiotemporal dynamical systems is a fundamental challenge in machine learning. Transformer models have been very successful in NLP and computer vision where they provide interpretable representations of data. However, a limitation of transformers in modeling continuous dynamical systems is that they are fundamentally discrete time and space models and thus have no guarantees regarding continuous sampling. To address this challenge, we present the Continuous Spatiotemporal Transformer (CST), a new transformer architecture that is designed for modeling of continuous systems. This new framework guarantees a continuous and smooth output via optimization in Sobolev space. We benchmark CST against traditional transformers as well as other spatiotemporal dynamics modeling methods and achieve superior performance in a number of tasks on synthetic and real systems, including learning brain dynamics from calcium imaging data.

Chat is not available.