Neural Expectation Maximization

Klaus Greff, Sjoerd van Steenkiste, Jürgen Schmidhuber

Abstract:

We introduce a novel framework for clustering that combines generalized EM
with neural networks and can be implemented as an end-to-end differentiable
recurrent neural network. It learns its statistical model directly from the data and
can represent complex non-linear dependencies between inputs. We apply our
framework to a perceptual grouping task and empirically verify that it yields the
intended behavior as a proof of concept.

TL;DR: A framework for clustering that combines generalized EM with neural networks and can be implemented as an end-to-end differentiable recurrent neural network

Keywords: Theory, Deep learning, Unsupervised Learning

Conflicts: usi.ch, idsia.ch, supsi.ch, cai.fi