no code implementations • 19 Jun 2020 • Agnes Korcsak-Gorzo, Michael G. Müller, Andreas Baumbach, Luziwei Leng, Oliver Julien Breitwieser, Sacha J. van Albada, Walter Senn, Karlheinz Meier, Robert Legenstein, Mihai A. Petrovici
Being permanently confronted with an uncertain world, brains have faced evolutionary pressure to represent this uncertainty in order to respond appropriately.
no code implementations • 30 Dec 2019 • Sebastian Billaudelle, Yannik Stradmann, Korbinian Schreiber, Benjamin Cramer, Andreas Baumbach, Dominik Dold, Julian Göltz, Akos F. Kungl, Timo C. Wunderlich, Andreas Hartel, Eric Müller, Oliver Breitwieser, Christian Mauch, Mitja Kleider, Andreas Grübl, David Stöckel, Christian Pehle, Arthur Heimbrecht, Philipp Spilger, Gerd Kiene, Vitali Karasenko, Walter Senn, Mihai A. Petrovici, Johannes Schemmel, Karlheinz Meier
We present first experimental results on the novel BrainScaleS-2 neuromorphic architecture based on an analog neuro-synaptic core and augmented by embedded microprocessors for complex plasticity and experiment control.
In computational neuroscience, as well as in machine learning, neuromorphic devices promise an accelerated and scalable alternative to neural network simulations.
3 code implementations • 24 Dec 2019 • Julian Göltz, Laura Kriener, Andreas Baumbach, Sebastian Billaudelle, Oliver Breitwieser, Benjamin Cramer, Dominik Dold, Akos Ferenc Kungl, Walter Senn, Johannes Schemmel, Karlheinz Meier, Mihai Alexandru Petrovici
For a biological agent operating under environmental pressure, energy consumption and reaction times are of critical importance.
In contrast, the hyperparameters and learning algorithms of networks of neurons in the brain, which they aim to emulate, have been optimized through extensive evolutionary and developmental processes for specific ranges of computing and learning tasks.
no code implementations • 8 Nov 2018 • Timo Wunderlich, Akos F. Kungl, Eric Müller, Andreas Hartel, Yannik Stradmann, Syed Ahmed Aamir, Andreas Grübl, Arthur Heimbrecht, Korbinian Schreiber, David Stöckel, Christian Pehle, Sebastian Billaudelle, Gerd Kiene, Christian Mauch, Johannes Schemmel, Karlheinz Meier, Mihai A. Petrovici
Neuromorphic devices represent an attempt to mimic aspects of the brain's architecture and dynamics with the aim of replicating its hallmark functional capabilities in terms of computational power, robust learning and energy efficiency.
An increasing body of evidence suggests that the trial-to-trial variability of spiking activity in the brain is not mere noise, but rather the reflection of a sampling-based encoding scheme for probabilistic computing.
no code implementations • 6 Jul 2018 • 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
The massively parallel nature of biological information processing plays an important role for its superiority to human-engineered computing devices.
Together with the Kirchhoff-Institute for Physics(KIP) the Fraunhofer IZM has developed a full wafer redistribution and embedding technology as base for a large-scale neuromorphic hardware system.
In this work, we use networks of leaky integrate-and-fire neurons that are trained to perform both discriminative and generative tasks in their forward and backward information processing paths, respectively.
This paper presents an extension of the BrainScaleS accelerated analog neuromorphic hardware model.
no code implementations • 17 Mar 2017 • Mihai A. Petrovici, Sebastian Schmitt, Johann Klähn, David Stöckel, Anna Schroeder, Guillaume Bellec, Johannes Bill, Oliver Breitwieser, Ilja Bytschok, Andreas Grübl, Maurice Güttler, Andreas Hartel, Stephan Hartmann, Dan Husmann, Kai Husmann, Sebastian Jeltsch, Vitali Karasenko, Mitja Kleider, Christoph Koke, Alexander Kononov, Christian Mauch, Eric Müller, Paul Müller, Johannes Partzsch, Thomas Pfeil, Stefan Schiefer, Stefan Scholze, Anand Subramoney, Vasilis Thanasoulis, Bernhard Vogginger, Robert Legenstein, Wolfgang Maass, René Schüffny, Christian Mayr, Johannes Schemmel, Karlheinz Meier
Despite being originally inspired by the central nervous system, artificial neural networks have diverged from their biological archetypes as they have been remodeled to fit particular tasks.
How spiking networks are able to perform probabilistic inference is an intriguing question, not only for understanding information processing in the brain, but also for transferring these computational principles to neuromorphic silicon circuits.
1 code implementation • 6 Mar 2017 • Sebastian Schmitt, Johann Klaehn, Guillaume Bellec, Andreas Gruebl, Maurice Guettler, Andreas Hartel, Stephan Hartmann, Dan Husmann, Kai Husmann, Vitali Karasenko, Mitja Kleider, Christoph Koke, Christian Mauch, Eric Mueller, Paul Mueller, Johannes Partzsch, Mihai A. Petrovici, Stefan Schiefer, Stefan Scholze, Bernhard Vogginger, Robert Legenstein, Wolfgang Maass, Christian Mayr, Johannes Schemmel, Karlheinz Meier
In this paper, we demonstrate how iterative training of a hardware-emulated network can compensate for anomalies induced by the analog substrate.
The highly variable dynamics of neocortical circuits observed in vivo have been hypothesized to represent a signature of ongoing stochastic inference but stand in apparent contrast to the deterministic response of neurons measured in vitro.
This processor is operating in parallel with a fully parallel neuromorphic system consisting of an array of synapses connected to analog, continuous time neuron circuits.
The core idea of our approach is to separately consider two different "modes" of spiking dynamics: burst spiking and transient quiescence, in which the neuron does not spike for longer periods.
no code implementations • 29 Apr 2014 • Mihai A. Petrovici, Bernhard Vogginger, Paul Müller, Oliver Breitwieser, Mikael Lundqvist, Lyle Muller, Matthias Ehrlich, Alain Destexhe, Anders Lansner, René Schüffny, Johannes Schemmel, Karlheinz Meier
Advancing the size and complexity of neural network models leads to an ever increasing demand for computational resources for their simulation.
The seemingly stochastic transient dynamics of neocortical circuits observed in vivo have been hypothesized to represent a signature of ongoing stochastic inference.
We describe an accelerated hardware neuron being capable of emulating the adap-tive exponential integrate-and-fire neuron model.