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

Building intelligent systems that are capable of extracting high-level representations from
high-dimensional sensory data lies at the core of solving many artificial intelligence–related …

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 …

Situation-aware technologies enabled by multitarget tracking will lead to new services and
applications in fields such as autonomous driving, indoor localization, robotic networks, and …

Empirical risk minimization (ERM) is typically designed to perform well on the average loss,
which can result in estimators that are sensitive to outliers, generalize poorly, or treat …

A general framework for constructing and using probabilistic models of complex systems that
would enable a computer to use available information for making decisions. Most tasks …

Model-based methods and deep neural networks have both been tremendously successful
paradigms in machine learning. In model-based methods, problem domain knowledge can …

The formalism of probabilistic graphical models provides a unifying framework for capturing
complex dependencies among random variables, and building large-scale multivariate …

The Bayesian framework for machine learning allows for the incorporation of prior
knowledge in a coherent way, avoids overfitting problems, and provides a principled basis …

Important inference problems in statistical physics, computer vision, error-correcting coding
theory, and artificial intelligence can all be reformulated as the computation of marginal …