Publications Neuro-inspired Theory, Modeling and Applications

M. Farisco, G. Baldassarre, E. Cartoni, A. Leach, M.A. Petrovici, A. Rosemann, A. Salles, B. Stahl, S. J. van Albada.
A method for the ethical analysis of brain-inspired AI. Artificial Intelligence Review 2024 DOI pdf

arXiv

W. Senn, Dold D., Kungl A.F., Ellenberger B, Jordan J., Bengio Y., Sacramento J. and Petrovici M.A..
A Neuronal Least-action Principle For Real-time Learning In Cortical Circuits. eLIFE 2024 DOI pdf

bioRxiv

B. Ellenberger, P. Haider, J. Jordan, K. Max, I. Jaras, L. Kriener, F. Benitez, M.A. Petrovici.
Backpropagation through space, time, and the brain. arXiv 2024 DOI pdf

J. Jordan, J. Sacramento, W.A.M. Wybo, M.A. Petrovici, W. Senn.
Conductance-based dendrites perform Bayes-optimal cue integration. PLoS Comput Biol 2024 DOI PubMed pdf

arXiv

A. Granier, M.A. Petrovici, W. Senn, K.A. Wilmes.
Confidence and second-order errors in cortical circuits. PNAS Nexus 2024 DOI PubMed pdf

arXiv

J. Göltz, J. Weber, L. Kriener, P. Lake, M. Payvand, M.A. Petrovici.
DelGrad: Exact gradients in spiking networks for learning transmission delays and weights. arXiv 2024 DOI pdf

N. Deperrois, M.A. Petrovici, J. Jordan, L.S. Huber, and W. Senn.
How Adversarial REM Dreams May Facilitate Creativity, and Why We Become Aware of Them. Clinical and Translational Neuroscience 2024 DOI pdf

preprints.org

B. von Hünerbein, J. Jordan, M.O. Lohuis, P. Marchesi, U. Olcese, C.M.A. Pennartz, W. Senn, M.A. Petrovici.
Increased perceptual reliability reduces membrane potential variability in cortical neurons. bioRxiv 2024 DOI pdf

K. Max, L. Kriener, G. Pineda Garcia, T. Nowotny, I. Jaras, W. Senn and M.A. Petrovici.
Learning efficient backprojections across cortical hierarchies in real time. Nature Machine Intelligence 2024 DOI pdf

arXiv

Y. Stradmann, J. Göltz, M.A. Petrovici, J. Schemmel, S. Billaudelle.
Lu.i - A low-cost electronic neuron for education and outreach. arXiv 2024 DOI pdf

L. Kriener, K. Völk, B. von Hünerbein, F. Benitez, W. Senn, M.A. Petrovici.
Order from chaos: Interplay of development and learning in recurrent networks of structured neurons. arXiv 2024 DOI pdf

S. Brandt, M.A. Petrovici, W. Senn, K.A. Wilmes, F. Benitez.
Prospective and retrospective coding in cortical neurons. arXiv 2024 DOI pdf

K. Amunts, (...), Mihai A. Petrovici, (...), W. Senn, (...).
The coming decade of digital brain research: A vision for neuroscience at the intersection of technology and computing. Imaging Neuroscience 2024 DOI pdf

Zenodo

K. Schreiber, T. Wunderlich, P. Spilger, S. Billaudelle, B. Cramer, Y. Stradmann, C. Pehle, E. Müller, M.A. Petrovici, J. Schemmel, K. Meier.
Emulating insect brains for neuromorphic navigation. arXiv 2023 DOI pdf

J. Göltz, S. Billaudelle, L. Kriener, L. Blessing, C. Pehle, E. Müller, J. Schemmel, M.A. Petrovici.
Gradient-based methods for spiking physical systems. arXiv 2023 DOI pdf

S. Chakrabarty, M.A. Petrovici.
Is neuromorphic computing disruptive enough to 1) advance our understanding of the brain and 2) make the design and working of (bio)electronic devices efficient and scalable?. Research Directions: Bioelectronics 2023 DOI pdf

N. Deperrois, M.A. Petrovici, W. Senn, J. Jordan.
Learning beyond sensations: how dreams organize neuronal representations. Neuroscience & Biobehavioral Reviews 2023 DOI pdf

arXiv

M. Senden, S.J. van Albada, G. Pezzulo, E. Falotico, I. Hashim, A. Kroner, A.C. Kurth, P. Lanillos, V. Narayanan, C. Pennartz, M.A. Petrovici, L. Steffen, T. Weidler, R. Goebel.
Modular-integrative modeling: a new framework for building brain models that blend biological realism and functional performance. National Science Review 2023 DOI pdf

J. Yik, ..., M.A. Petrovici et al..
NeuroBench: Advancing Neuromorphic Computing through Collaborative, Fair and Representative Benchmarking. arXiv 2023 DOI pdf

K.A. Wilmes, M.A. Petrovici, S. Sachidhanandam and W. Senn.
Uncertainty-modulated prediction errors in cortical microcircuits. bioRxiv 2023 DOI pdf

A. Korcsak-Gorzo, M.G. Müller, A. Baumbach, L. Leng, O.J. Breitwieser, S.J. van Albada, W. Senn, K. Meier, R. Legenstein, M. A. Petrovici.
Cortical oscillations support sampling-based computations in spiking neural networks. PLoS Comput Biol 2022 DOI PubMed pdf

arXiv

C. Gontier, J. Jordan, M.A. Petrovici.
DELAUNAY: a dataset of abstract art for psychophysical and machine learning research. arXiv 2022 DOI pdf

GitHub project

N. Deperrois, M.A. Petrovici, W. Senn, and J. Jordan.
Learning cortical representations through perturbed and adversarial dreaming. eLIFE 2022 DOI pdf

arXiv

E. Kreutzer, W. Senn, M.A. Petrovici.
Natural-gradient learning for spiking neurons. eLIFE 2022 DOI pdf

arXiv

S. Czischek, A. Baumbach, S. Billaudelle, B. Cramer, L. Kades, J.M. Pawlowski, M.K. Oberthaler, J. Schemmel, M.A. Petrovici, T. Gasenzer and M. Gärttner.
Spiking neuromorphic chip learns entangled quantum states. SciPost Physics 39, 2022 DOI pdf

arXiv

L. Kriener, J. Göltz, M. A. Petrovici.
The Yin-Yang dataset. Neuro-Inspired Computational Elements Conference Proceedings 2022 DOI pdf

arXiv

R. Klassert, A. Baumbach, M.A. Petrovici, and M. Gärttner.
Variational learning of quantum ground states on spiking neuromorphic hardware. iScience 2022 DOI pdf

arXiv

A. Baumbach, S. Billaudelle, V. Sabado and M.A. Petrovici.
BrainScaleS: Greater Versatility for Neuromorphic Emulation. ERCIM April, 2021

Article

J. Jordan, M. Schmidt, W. Senn, M.A. Petrovici.
Evolving interpretable plasticity for spiking networks. eLIFE 2021 DOI PubMed pdf

arXiv

H.D. Mettler, M. Schmidt, W. Senn, M.A. Petrovici, J. Jordan.
Evolving Neuronal Plasticity Rules using Cartesian Genetic Programming. arXiv 2021 DOI pdf

J. Göltz, L. Kriener, V. Sabado and M.A. Petrovici.
Fast and Energy-efficient Deep Neuromorphic Learning. ERCIM April, 2021

Article

J. Göltz, L. Kriener, A. Baumbach, S. Billaudelle, O. Breitwieser, B. Cramer, D. Dold, A.F. Kungl, W. Senn, J. Schemmel, K. Meier, M.A. Petrovici.
Fast and energy-efficient neuromorphic deep learning with first-spike times. Nature Machine Intelligence 823–835, 2021 DOI pdf

arXiv

P. Haider, B. Ellenberger, L. Kriener, J. Jordan, W. Senn, M.A. Petrovici.
Latent Equilibrium: A unified learning theory for arbitrarily fast computation with arbitrarily slow neurons. Advances in Neural Information Processing Systems (NeurIPS) 2021 pdf

Peer-reviewed conference article - Advances in Neural Information Processing Systems 34 (NeurIPS 2021)

arXiv

C. Zhao, Y.F. Widmer, S. Diegelmann, M.A. Petrovici, S.G. Sprecher, W. Senn.
Predictive olfactory learning in Drosophila. Sci Rep 2021 DOI PubMed pdf

bioRxiv

S. Billaudelle, B. Cramer, M.A. Petrovici, K. Schreiber, D. Kappel, J. Schemmel, K. Meier.
Structural plasticity on an accelerated analog neuromorphic hardware system. Neural Networks 133, 11-20, 2021 DOI pdf

arXiv

H.D. Mettler, V. Sabado, W. Senn, M.A. Petrovici and J. Jordan .
Uncovering Neuronal Learning Principles through Artificial Evolution. ERCIM April, 2021

Article

F. Zenke, S.M. Bohté, C. Clopath, I.M. Comşa, J. Göltz, W. Maass, T. Masquelier, R. Naud, E.O. Neftci, M.A. Petrovici, F. Scherr, and D.F.M. Goodman.
Visualizing a joint future of neuroscience and neuromorphic engineering. Neuron 571-575, 2021 DOI

S. Billaudelle, Y. Stradmann, K. Schreiber, B. Cramer, A. Baumbach, D. Dold, J. Göltz, A.F. Kungl, T.C. Wunderlich, A. Hartel, E. Müller, O. Breitwieser, C. Mauch, M. Kleider, A. Grübl, Da. Stöckel, C. Pehle, A. Heimbrecht, P. Spilger, G. Kiene, V. Karasenko, W. Senn, M.A. Petrovici, J. Schemmel, K. Meier.
Versatile emulation of spiking neural networks on an accelerated neuromorphic substrate. IEEE Xplore 2020 DOI pdf

arXiv

A.F. Kungl, S. Schmitt, J. Klähn, P. Müller, A. Baumbach, D. Dold, A. Kugele, N. Gürtler, E. Müller, C. Koke, M. Kleider, C. Mauch, O. Bretwieser, M. Güttler, D. Husmann, K. Husmann, J. Ilmberger, A. Hartel, V. Karasenko, A. Grübl, J. Schemmel, K. Meier, M.A. Petrovici.
Accelerated physical emulation of Bayesian inference in spiking neural networks. Front. Neuroscience 2019 DOI pdf

arXiv

T. Wunderlich, A.F. Kungl, E. Müller, A. Hartel, Y. Stradmann, S. A. Aamir, A. Grübl, A. Heimbrecht, K. Schreiber, D. Stöckel, C. Pehle, S. Billaudelle, G. Kiene, C. Mauch, J. Schemmel, K. Meier and M.A. Petrovici.
Demonstrating Advantages of Neuromorphic Computation: A Pilot Study. Front. Neuroscience 3:260, 2019 DOI pdf

arXiv

J. Jordan, M.A. Petrovici, O. Breitwieser, J. Schemmel, K. Meier, M. Diesmann & T. Tetzlaff.
Deterministic networks for probabilistic computing. Nature Scientific Reports 9:18303, 2019 DOI pdf

arXiv

D. Dold, A.F. Kungl, J. Sacramento, M.A. Petrovici, K. Schindler, J. Binas, Y. Bengio, W. Senn.
Lagrangian neurodynamics for real-time error-backpropagation across cortical areas. 2019 pdf

D. Dold, I. Bytschok, A.F. Kungl, A. Baumbach, O. Breitwieser, W. Senn, J. Schemmel, K. Meier, M.A. Petrovici.
Stochasticity from function - Why the Bayesian brain may need no noise. Neural Networks 2019 DOI pdf

arXiv

Luziwei Leng, R. Martel, O. Breitwieser, I. Bytschok, W. Senn, J. Schemmel, K. Meier & M.A. Petrovici .
Spiking neurons with short-term synaptic plasticity form superior generative networks. Nature Scientific Reports 8: 10651, 2018 DOI pdf

arXiv

S. Schmitt, J. Klähn, G. Bellec, A. Grübl, M. Güttler, A. Hartel, S. Hartmann, D. Husmann, K. Husmann, S. Jeltsch, V. Karasenko, M. Kleider, C. Koke, A. Kononov, C. Mauch, E. Müller, P. Müller, J. Partzsch, M.A. Petrovici, S. Schiefer, S. Scholze, V. Thanasoulis, B. Vogginger, R. Legenstein, W. Maass, C. Mayr, R. Schüffny, J. Schemmel, K. Meier.
Neuromorphic hardware in the loop: Training a deep spiking network on the BrainScaleS wafer-scale system. Proceedings of 2017 IJCNN online, 2017 DOI pdf

arXiv

M.A. Petrovici, S. Schmitt, J. Klähn, D. Stöckel, A. Schroeder, G. Bellec, J. Bill, O. Breitwieser, I. Bytschok, A. Grübl, M. Güttler, A. Hartel, S. Hartmann, D. Husmann, K. Husmann, S. Jeltsch, V. Karasenko, M. Kleider, C. Koke, A. Kononov, C. Mauch, E. Müller, P. Müller, J. Partzsch, T. Pfeil, S. Schiefer, S. Scholze, A. Subramoney, V. Thanasoulis, B. Vogginger, R. Legenstein, W. Maass, R. Schüffny, C. Mayr, J. Schemmel, K. Meier.
Pattern representation and recognition with accelerated analog neuromorphic systems. Proceedings of 2017 IEEE International Symposium on Circuits and Systems (ISCAS) 2017 DOI pdf

arXiv

M.A. Petrovici, A. Schroeder, O. Breitwieser, A. Grübl, J. Schemmel, K. Meier.
Robustness from structure: Inference with hierarchical spiking networks on analog neuromorphic hardware. Proceedings of 2017 IJCNN online, 2017 DOI pdf

arXiv

M.A. Petrovici.
Form Versus Function: Theory and Models for Neuronal Substrates . 2016 DOI pdf

M.A. Petrovici, J. Bill, I. Bytschok, J. Schemmel, K. Meier.
Stochastic inference with spiking neurons in the high-conductance state. Phys. Rev. E 042312, 2016 DOI

arXiv

D. Probst, M.A. Petrovici, I. Bytschok, J. Bill, D. Pecevski, J. Schemmel, K. Meier.
Probabilistic inference in discrete spaces can be implemented into networks of LIF neurons. Front. Comput.Neurosci. 2015 DOI

arXiv

M.A. Petrovici, B. Vogginger, P. Müller, O. Breitwieser, M. Lundqvist, L. Muller, M. Ehrlich, A. Destexhe, A. Lansner, R. Schüffny, J. Schemmel, K. Meier .
Characterization and Compensation of Network-Level Anomalies in Mixed-Signal Neuromorphic Modeling Platforms. PLoS ONE 2014 DOI

arXiv

T. Pfeil, A. Grübl, S. Jeltsch, E. Müller, P. Müller, M.A. Petrovici, M. Schmuker, D. Brüderle, J. Schemmel, K. Meier.
Six networks on a universal neuromorphic computing substrate. Front. Neuroscience 2013 DOI

arXiv

M.A. Petrovici, J. Bill, I. Bytschok, J. Schemmel, K. Meier.
Stochastic inference with deterministic spiking neurons. arXiv 2013 DOI pdf

D. Brüderle, M.A. Petrovici, B. Vogginger, M. Ehrlich, T. Pfeil, S. Millner, A. Grübl, K. Wendt, E. Müller and M.O. Schwartz, K. Meier .
A comprehensive workflow for general-purpose neural modeling with highly configurable neuromorphic hardware systems. Biological Cybernetics 104, pages263–296, 2011 DOI

arXiv