As a consequence, BO is useful when function evaluation is time-consuming, such as when training and testing complex machine learning algorithms (e.g.

We employ a reclassification-by-synthesis algorithm to perform training using a formulation stemmed from the Bayes theory.

Neural Information Processing Systems http://nips.cc/

Learning with deep neural networks has enjoyed huge empirical success in recent years across a wide variety of tasks.

The list of successful applications of deep learning is growing at a staggering rate. Image recognition (Krizhevsky et al., 2012), audio synthesis (Oord et al., 2016), translation (Wu et al., 2016), and speech recognition (Hinton et al., 2012) are just a few of the recent achievements.

In this section we describe the mathematical framework underlying Distral.

Many cognitive tasks require learning useful representations on multiple abstraction levels. Hierarchical latent variable models are an appealing approach for learning a hierarchy of abstractions.

Neural Information Processing Systems http://nips.cc/

Work was done while at Facebook AI Research.

Therefore a reasonable alternative is to be able to automatically generate new annotated training samples using a process known as data augmentation.