This paper provides a concise description of the free energy principle, starting from a
formulation of random dynamical systems in terms of a Langevin equation and ending with a …

This review considers computational psychiatry from a particular viewpoint: namely, a
commitment to explaining psychopathology in terms of pathophysiology. It rests on the …

The first comprehensive treatment of active inference, an integrative perspective on brain,
cognition, and behavior used across multiple disciplines. Active inference is a way of …

Variational autoencoders (VAEs) are powerful deep generative models widely used to
represent high-dimensional complex data through a low-dimensional latent space learned …

This paper is a broad and accessible survey of the methods we have at our disposal for
Monte Carlo gradient estimation in machine learning and across the statistical sciences: the …

The active inference framework, and in particular its recent formulation as a partially
observable Markov decision process (POMDP), has gained increasing popularity in recent …

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 …

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

PowerPoint 演示文稿 Page 1 Uncertainty in Deep Learning Yarin Gal 2018.7.29 Page 2 Page
3 Different Uncertainties Two main types of uncertainty, often confused by practitioners, but …

Probabilistic modeling is iterative. A scientist posits a simple model, fits it to her data, refines
it according to her analysis, and repeats. However, fitting complex models to large data is a …