R Salakhutdinov - Annual Review of Statistics and Its Application, 2015 - annualreviews.org
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 …