Many modern unsupervised or semi-supervised machine learning algorithms rely on
Bayesian probabilistic models. These models are usually intractable and thus require …

We propose a new regularization method based on virtual adversarial loss: a new measure
of local smoothness of the conditional label distribution given input. Virtual adversarial loss …

We formulate a general framework for building structural causal models (SCMs) with deep
learning components. The proposed approach employs normalising flows and variational …

In many domains, including healthcare, biology, and climate science, time series are
irregularly sampled with varying time intervals between successive readouts and different …

Motivation Models for analysing and making relevant biological inferences from massive
amounts of complex single-cell transcriptomic data typically require several individual data …

Noninvasive behavioral tracking of animals is crucial for many scientific investigations.
Recent transfer learning approaches for behavioral tracking have considerably advanced …

Conventional variational autoencoders fail in modeling correlations between data points
due to their use of factorized priors. Amortized Gaussian process inference through GP …

Probabilistic Latent Variable Models (LVMs) provide an alternative to self-supervised
learning approaches for linguistic representation learning from speech. LVMs admit an …

Large, multi-dimensional spatio-temporal datasets are omnipresent in modern science and
engineering. An effective framework for handling such data are Gaussian process deep …

Deep neural networks have bested notable benchmarks across computer vision,
reinforcement learning, speech recognition, and natural language processing. However …