Models using structured state space sequence (S4) layers have achieved state-of-the-art
performance on long-range sequence modeling tasks. An S4 layer combines linear state …

State estimation of dynamical systems in real-time is a fundamental task in signal
processing. For systems that are well-represented by a fully known linear Gaussian state …

Leveraging physical knowledge described by partial differential equations (PDEs) is an
appealing way to improve unsupervised video forecasting models. Since physics is too …

For speaker recognition, it is difficult to extract an accurate speaker representation from
speech because of its mixture of speaker traits and content. This paper proposes a …

Forecasting complex dynamical phenomena in settings where only partial knowledge of
their dynamics is available is a prevalent problem across various scientific fields. While …

The large and catastrophic wildfires have been increasing across the globe in the recent
decade, highlighting the importance of simulating and forecasting fire dynamics in near real …

Recurrent neural networks (RNNs) are a popular choice for modeling sequential data.
Modern RNN architectures assume constant time-intervals between observations. However …

Reduced-order modelling and low-dimensional surrogate models generated using machine
learning algorithms have been widely applied in high-dimensional dynamical systems to …

We consider the problem of variational Bayesian inference in a latent variable model where
a (possibly complex) observed stochastic process is governed by the unobserved solution of …

In this paper, we present SSDNet, a novel deep learning approach for time series
forecasting. SSDNet combines the Transformer architecture with state space models to …