Publications

Books


Form versus function: theory and models for neuronal substrates

Mihai A. Petrovici

Springer Theses 2016, ISBN 978-3-319-39551-7 (Springer Thesis Award)


Articles


Spiking neuromophic chip learns entangled quantum states

Stefanie Czischek, Andreas Baumbach, Sebastian Billaudelle, Benjamin Cramer, Lukas Kades, Jan M. Pawlowski, Markus K. Oberthaler, Johannes Schemmel, Mihai A. Petrovici, Thomas Gasenzer, Martin Gärttner

arXiv:2008.01039


Evolving to learn: discovering interpretable plasticity rules for spiking networks

Jakob Jordan*, Maximilian Schmidt*, Walter Senn, Mihai A. Petrovici

arXiv:2005.14149


Predictive olfactory learning in Drosophila

Chang Zhao, Yves F. Widmer, Soeren Diegelmann, Mihai A. Petrovici, Simon G. Sprecher, Walter Senn

bioRxiv: 10.1101/2019.12.29.890533


Versatile emulation of spiking neural networks on an accelerated neuromorphic substrate

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°

arXiv:1912.12980 (2019)


Structural plasticity on an accelerated analog neuromorphic hardware system

Sebastian Billaudelle*, Benjamin Cramer*, Mihai A. Petrovici, Korbinian Schreiber, David Kappel, Johannes Schemmel, Karlheinz Meier

arXiv:1912.12047 (2019)


Fast and deep neuromorphic learning with time-to-first-spike coding

Julian Göltz, Andreas Baumbach, Sebastian Billaudelle, Oliver Breitwieser, Dominik Dold, Laura Kriener, Akos Ferenc Kungl, Walter Senn, Johannes Schemmel, Karlheinz Meier, Mihai A. Petrovici

arXiv:1912.11443 (2019)


Deterministic networks for stochastic computing

Jakob Jordan, Mihai A. Petrovici, Oliver Breitwieser, Johannes Schemmel, Karlheinz Meier, Markus Diesmann, Tom Tetzlaff

Scientific Reports 9, 18303 (2019)


Stochasticity from function - why the Bayesian brain may need no noise

Dominik Dold*, Ilja Bytschok*, Akos F. Kungl, Andreas Baumbach, Oliver Breitwieser, Walter Senn, Johannes Schemmel, Karlheinz Meier, Mihai A. Petrovici*

Neural Networks 119 (2019)


Accelerated physical emulation of Bayesian inference in spiking neural networks

Akos F. Kungl, Sebastian Schmitt, Johann Klähn, Paul Müller, Andreas Baumbach, Dominik Dold, Alexander Kugele, Nico Gürtler, Eric Müller, Christoph Koke, Mitja Kleider, Christian Mauch, Oliver Bretwieser, Maurice Güttler, Dan Husmann, Kai Husmann, Joscha Ilmberger, Andreas Hartel, Vitali Karasenko, Andreas Grübl, Johannes Schemmel, Karlheinz Meier, Mihai A. Petrovici

Frontiers in Neuroscience 13, 1201 (2019)


Demonstrating Advantages of Neuromorphic Computation: A Pilot Study

Timo Wunderlich, Akos F. Kungl, 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

Frontiers in Neuroscience, 13, 260 (2019)


Spiking neurons with short-term synaptic plasticity form superior generative networks

Luziwei Leng*, Roman Martel, Oliver Breitwieser, Ilja Bytschok, Walter Senn, Johannes Schemmel, Karlheinz Meier, Mihai A. Petrovici*

Scientific Reports 8, 10651 (2018)


Pattern representation and recognition with accelerated analog neuromorphic systems

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, 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

Proceedings of the IEEE International Symposium on Circuits and Systems (2017)


Robustness from structure: Inference with hierarchical spiking networks on analog neuromorphic hardware

Mihai A. Petrovici*, Anna Schroeder*, Oliver Breitwieser, Andreas Grübl, Johannes Schemmel, Karlheinz Meier

Proceedings of the IEEE International Joint Conference on Neural Networks (2017)


Neuromorphic Hardware In The Loop: Training a Deep Spiking Network on the BrainScaleS Wafer-Scale System

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

Proceedings of the IEEE International Joint Conference on Neural Networks (2017)


Stochastic inference with spiking neurons in the high-conductance state

Mihai A. Petrovici*, Johannes Bill*, Ilja Bytschok, Johannes Schemmel, Karlheinz Meier

Physical Review E 94, 042312 (2016)


Probabilistic inference in discrete spaces can be implemented into networks of LIF neurons

Dimitri Probst*, Mihai A. Petrovici*, Ilja Bytschok, Johannes Bill, Dejan Pecevski, Johannes Schemmel, Karlheinz Meier

Frontiers in Computational Neurocience 9 (2015)


Characterization and Compensation of Network-Level Anomalies in Mixed-Signal Neuromorphic Modeling Platforms

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

PLOS ONE e108590 (2014)


Stochastic inference with deterministic spiking neurons

Mihai A. Petrovici*, Johannes Bill*, Ilja Bytschok, Johannes Schemmel, Karlheinz Meier

arXiv 1311.3211 (2013)


Six networks on a universal neuromorphic computing substrate

Thomas Pfeil*, Andreas Grübl*, Sebastian Jeltsch*, Eric Müller*, Paul Müller*, Mihai A. Petrovici*, Michael Schmuker*, Daniel Brüderle, Johannes Schemmel, Karlheinz Meier

Frontiers in Neuroscience 7 (2013)


A comprehensive workflow for general-purpose neural modeling with highly configurable neuromorphic hardware systems

Daniel Brüderle, Mihai A. Petrovici, Bernhard Vogginger, Matthias Ehrlich, Thomas Pfeil, Sebastian Millner, Andreas Grübl, Karsten Wendt, Eric Müller, Marc-Olivier Schwartz, Dan Husmann de Oliveira, Sebastian Jeltsch, Johannes Fieres, Moritz Schilling, Paul Müller, Oliver Breitwieser, Venelin Petkov, Lyle Muller, Andrew P. Davison, Pradeep Krishnamurthy, Jens Kremkow, Mikael Lundqvist, Eilif Muller, Johannes Partzsch, Stefan Scholze, Lukas Zühl, Christian Mayr, Alain Destexhe, Markus Diesmann, Tobias C. Potjans, Anders Lansner, René Schüffny, Johannes Schemmel, Karlheinz Meier

Biological Cybernetics 104, no. 4-5, 263-296 (2011)


ALICE: Physics Performance Report

The ALICE Collaboration

Journal of Physics G: Nuclear and Particle Physics 30 (11), 1517 (2004)


Conference abstracts, posters, demonstrations


Deep reinforcement learning for time-continuous substrates

Akos F. Kungl*, Dominik Dold*, Oskar Riedler, Mihai A. Petrovici, Walter Senn

Neuro-Inspired Computational Elements Workshop (NICE) 2020


Natural gradient learning for spiking neurons

E. Kreutzer, M. A. Petrovici°, W. Senn°

Computational and Systems Neuroscience (Cosyne) 2020, Neuro-Inspired Computational Elements Workshop (NICE) 2020


Fast and deep neuromorphic learning with first-spike coding

J. Göltz, A. Baumbach, S. Billaudelle, O. Breitwieser, L. Kriener, A. F. Kungl, K. Meier, J. Schemmel, M. A. Petrovici

Computational and Systems Neuroscience (Cosyne) 2020, Neuro-Inspired Computational Elements Workshop (NICE) 2020, From Neuroscience to Artificially Intelligent Systems (NAISys) 2020


Conductance-based dendrites perform reliability-weighted opinion pooling

Jakob Jordan, Mihai A. Petrovici, Walter Senn, João Sacramento

Computational and Systems Neuroscience (Cosyne) 2020, Neuro-Inspired Computational Elements Workshop (NICE) 2020, From Neuroscience to Artificially Intelligent Systems (NAISys) 2020


Closed-loop experiments on the BrainScaleS-2 architecture

K. Schreiber, T. C. Wunderlich, C. Pehle, M. A. Petrovici°, J. Schemmel°, K. Meier°

Neuro-Inspired Computational Elements Workshop (NICE) 2020


Structural plasticity on spiking neuromorphic hardware

Sebastian Billaudelle, Benjamin Cramer, Mihai A. Petrovici, Johannes Schemmel

Neuro-Inspired Computational Elements Workshop (NICE) 2020


An energy-based model of folded autoencoders for unsupervised learning in cortical hierarchies

Dominik Dold, João Sacramento, Akos F. Kungl, Walter Senn and Mihai A. Petrovici

Bernstein Conference - Berlin, 2019


Deep reinforcement learning in a time-continuous model

Akos F. Kungl, Dominik Dold, Oskar Riedler, Mihai A. Petrovici, Walter Senn

Bernstein Conference - Berlin, 2019


Magnetic phenomena in ensembles of spiking neurons

Andreas Baumbach, Johannes Schemmel, Mihai A. Petrovici

Bernstein Conference - Berlin, 2019


Biological solutions to the mixing problem

Luziwei Leng, Agnes Korcsák-Gorzó, Oliver Breitwieser, Roman Martel, Ilja Bytschok, Walter Senn, Johannes Bill, Johannes Schemmel, Karlheinz Meier, Mihai A. Petrovici

IRCN 2019, best poster award


Brain-Inspired Hardware for Artificial Intelligence: Accelerated Learning in a Physical-Model Spiking Neural Network

Timo Wunderlich, Akos F. Kungl, Eric Müller, Johannes Schemmel, Mihai A. Petrovici

ICANN - Theoretical neural computation / Lecture Notes on Computer Science 11727, 119-122 (2019)


Lagrangian dynamics of dendritic microcircuits enables real-time backpropagation of errors

Dominik Dold, Akos F. Kungl, João Sacramento, Mihai A. Petrovici, Kaspar Schindler, Jonathan Binas, Yoshua Bengio, Walter Senn

Selected talk at Cosyne (2019)


Error-driven learning supports Bayes-optimal multisensory integration via conductance-based dendrites

Jakob Jordan, João Sacramento, Mihai A Petrovici, Walter Senn

Cosyne abstracts (2019)


Magnetic Phenomena in Spiking Neural Networks

A. Baumbach, A. F. Kungl, M. A. Petrovici, J. Schemmel, K. Meier

Fruehjahrstagung der DPG (2018)


Bayesian computing with spikes

A. Baumbach, M. A. Petrovici, L. Leng, O. J. Breitwieser, D. Stoeckel, I. Bytschok, J. Schemmel, K. Meier

1st HBP Student Conference (2017)


Simulated Tempering in Biologically Inspired Neural Networks

Agnes Korcsak-Gorzo, Luziwei Leng, Oliver Julien Breitwieser, Johannes Schemmel, Karlheinz Meier, Mihai Alexandru Petrovici

Deutsche Physikerinnentagung (2017)


Stochastic computation on spiking neuromorphic hardware

Dominik Dold, Ákos F. Kungl, Andreas Baumbach, Johann Klähn, Ilja Bytschok, Paul Müller, Oliver Breitwieser, Andreas Grübl, Maurice Güttler, Dan Husmann, Mitja Kleider, Christoph Koke, Alexander Kugele, Christian Mauch, Eric Müller, Sebastian Schmitt, Johannes Schemmel, Karlheinz Meier, Mihai A. Petrovici

Bernstein Conference (2017)


Spike-based probabilistic inference with correlated noise

Ilja Bytschok*, Dominik Dold*, Johannes Schemmel, Karlheinz Meier, Mihai A. Petrovici*

CNS / BMC Neuroscience 18 (Suppl 1):P200 (2017)


Stochastic inference with spiking neural networks

Mihai A. Petrovici*, Luziwei Leng*, Oliver Breitwieser*, David Stöckel*, Ilja Bytschok, Roman Martel, Johannes Bill, Johannes Schemmel, Karlheinz Meier

CNS / BMC Neuroscience 17(Suppl 1):P96 (2016)


Spiking neural networks as superior generative and discriminative models

Luziwei Leng*, Mihai A. Petrovici*, Roman Martel, Ilja Bytschok, Oliver Breitwieser, Johannes Bill, Johannes Schemmel, Karlheinz Meier

Cosyne Abstracts (2016)


Fast sampling with neuromorphic hardware

Mihai A. Petrovici*, David Stöckel*, Ilja Bytschok, Johannes Bill, Thomas Pfeil, Johannes Schemmel, Karlheinz Meier

Demonstration, Advances in Neural Information Processing Systems (NIPS) 28, (2015)


The high-conductance state enables neural sampling in networks of LIF neurons

Mihai A. Petrovici, Ilja Bytschok, Johannes Bill, Johannes Schemmel and Karlheinz Meier

CNS / BMC Neuroscience 16(Suppl 1):O2, selected for oral presentation (2015)


Deterministic neural networks as sources of uncorrelated noise for probabilistic computations

Jakob Jordan, Tom Tetzlaff, Mihai Petrovici, Oliver Breitwieser, Ilja Bytschok, Johannes Bill, Johannes Schemmel, Karlheinz Meier and Markus Diesmann

CNS / BMC Neuroscience 16(Suppl 1):P62 (2015)


 
up