Original Research ARTICLE
Accelerated physical emulation of Bayesian inference in spiking neural networks
- 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, firstname.lastname@example.org