From Deep Learning of Disentangled Representations to Higher level Cognition

One of the main challenges for AI remains unsupervised learning, at which humans are much better than machines, and which we link to another challenge: bringing deep learning to higherlevel cognition. We review earlier work on the notion of learning disentangled representations and deep generative models and propose research directions towards learning of highlevel abstractions. This follows the ambitious objective of disentangling the underlying causal factors explaining the observed data. We argue that