KIP-Veröffentlichungen

 
Jahr 2019
Autor(en) Akos F. Kungl, Sebastian Schmitt, Johann Klähn, Paul Müller, Andreas Baumbach, Dominik Dold, Alexander Kugele, Nico Gürtler, Luziwei Leng, Eric Müller, Christoph Koke, Mitja Kleider, Christian Mauch, Oliver Breitwieser, Maurice Güttler, Dan Husmann, Kai Husmann, Joscha Ilmberger, Andreas Hartel, Vitali Karasenko, Andreas Grübl, Johannes Schemmel, Karlheinz Meier, Mihai A. Petrovici
Titel Accelerated physical emulation of Bayesian inference in spiking neural networks
KIP-Nummer HD-KIP 19-41
KIP-Gruppe(n) F9
Dokumentart Paper
Keywords Sampling, neuromorphic engineering, spiking neurons, physical emulation, inference, generative models
Quelle Frontiers in Neuroscience 13 (2019) 1201
doi 10.3389/fnins.2019.01201
Abstract (en)

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.

bibtex
@article{kungl2019accelerated,
  author   = {Kungl, Akos F and Schmitt, Sebastian and Kl{\"a}hn, Johann and M{\"u}ller, Paul and Baumbach, Andreas and Dold, Dominik and Kugele, Alexander and G{\"u}rtler, Nico and M{\"u}ller, Eric and Koke, Christoph and others},
  title    = {Accelerated physical emulation of Bayesian inference in spiking neural networks},
  journal  = {Frontiers in Neuroscience},
  year     = {2019},
  volume   = {13},
  pages    = {1201},
  doi      = {10.3389/fnins.2019.01201},
  url      = {https://www.frontiersin.org/articles/10.3389/fnins.2019.01201/abstract}
}
Referenz
URL arXiv
URL Journal Publication
Datei pdf
zum Seitenanfang
KIP - Bibliothek
Im Neuenheimer Feld 227
Raum 3.402
69120 Heidelberg