Impact Factor 3.648 | CiteScore 3.99
More on impact ›

Original Research ARTICLE Provisionally accepted The full-text will be published soon. Notify me

Front. Neurosci. | doi: 10.3389/fnins.2019.01201

Accelerated physical emulation of Bayesian inference in spiking neural networks

 Akos F. Kungl1*,  Sebastian Schmitt1, Johann Klähn1,  Paul Müller1,  Andreas Baumbach1,  Dominik Dold1,  Alexander Kugele1,  Eric Müller1, Christoph Koke1, Mitja Kleider1, Christian Mauch1, Oliver Breitwieser1, Luziwei Leng1, Nico Gürtler1, Maurice Güttler1, Dan Husmann1, Kai Husmann1,  Andreas Hartel1, Vitali Karasenko1,  Andreas Grübl1,  Johannes Schemmel1,  Karlheinz Meier1 and  Mihai A. Petrovici1, 2
  • 1Kirchhoff-Institute of Physics, Heidelberg University, Germany
  • 2Institut für Physiologie, Universität Bern, Switzerland

The massively parallel nature of biological information processing plays an important role for its superiority to human-engineered computing devices.
In particular, it may hold the key to overcoming the von Neumann bottleneck that limits contemporary computer architectures.
Physical-model neuromorphic devices seek to replicate not only this inherent parallelism, but also aspects of its microscopic dynamics in analog circuits emulating neurons and synapses.
However, these machines require network models that are not only adept at solving particular tasks, but that can also cope with the inherent imperfections of analog substrates.
We present a spiking network model that performs Bayesian inference through sampling on the BrainScaleS neuromorphic platform, where we use it for generative and discriminative computations on visual data.
By illustrating its functionality on this platform, we implicitly demonstrate its robustness to various substrate-specific distortive effects, as well as its accelerated capability for computation.
These results showcase the advantages of brain-inspired physical computation and provide important building blocks for large-scale neuromorphic applications.

Keywords: physical models, neuromorphic engineering, massively parallel computing, spiking neurons, recurrent neural networks, neural sampling, Probabilistic inference

Received: 10 Jul 2019; Accepted: 23 Oct 2019.

Copyright: © 2019 Kungl, Schmitt, Klähn, Müller, Baumbach, Dold, Kugele, Müller, Koke, Kleider, Mauch, Breitwieser, Leng, Gürtler, Güttler, Husmann, Husmann, Hartel, Karasenko, Grübl, Schemmel, Meier and Petrovici. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

* Correspondence: Mx. Akos F. Kungl, Kirchhoff-Institute of Physics, Heidelberg University, Heidelberg, Germany, fkungl@kip.uni-heidelberg.de