Dr. Robert Legenstein

Associate Professor

Institute for Theoretical Computer Science

Graz University of Technology


Research       Teaching      Publications


Publications

  • [40] A. Serb, J. Bill, A. Khiat, R. Berdan, R. Legenstein, and T. Prodromakis. Unsupervised learning in probabilistic neural networks with multi-state metal-oxide memristive synapses. Nature Communications, 2016. in press.

  • [39] Z. Yu, D. Kappel, R. Legenstein, S. Song, F. Chen, and W. Maass. Hamiltonian synaptic sampling in a model for reward-gated network plasticity. arXiv:1606.00157, 2016. (PDF). (link to the PDF)

  • [38] D. Kappel, S. Habenschuss, R. Legenstein, and W. Maass. Synaptic sampling: A Bayesian approach to neural network plasticity and rewiring. In Advances in Neural Information Processing Systems 28, C. Cortes, N. D. Lawrence, D. D. Lee, M. Sugiyama, and R. Garnett, editors, pages 370-378. Curran Associates, Inc., 2015. (PDF).

  • [37] J. Bill, L. Buesing, S. Habenschuss, B. Nessler, W. Maass, and R. Legenstein. Distributed Bayesian computation and self-organized learning in sheets of spiking neurons with local lateral inhibition. PLOS ONE, 10(8):e0134356, 2015. (Journal link to the PDF)

  • [36] R. Legenstein. Nanoscale connections for brain-like circuits. Nature, 521:37-38, 2015. (PDF).

  • [35] D. Kappel, S. Habenschuss, R. Legenstein, and W. Maass. Network plasticity as Bayesian inference. PLOS Computational Biology, 11(11):e1004485, 2015. (Journal link to the PDF)

  • [34] R. Legenstein. Recurrent network models, reservoir computing. In Encyclopedia of Computational Neuroscience, pages 1-5. Springer New York, 2014.

  • [33] J. Bill and R. Legenstein. A compound memristive synapse model for statistical learning through STDP in spiking neural networks. Frontiers in Neurosciense, 8(214):1-18, 2014. (Journal link to PDF)

  • [32] R. Legenstein and W. Maass. Ensembles of spiking neurons with noise support optimal probabilistic inference in a dynamically changing environment. PLOS Computational Biology, 10(10):e1003859, 2014. (Journal link to the PDF)

  • [31] A. V. Blackman, S. Grabuschnig, R. Legenstein, and P. J. Sjöström. A comparison of manual neuronal reconstruction from biocytin histology or 2-photon imaging: morphometry and computer modeling. Frontiers in neuroanatomy, 8, 2014. (Journal link to the PDF)

  • [30] G. Indiveri, B. Linares-Barranco, R. Legenstein, G. Deligeorgis, and T. Prodromakis. Integration of nanoscale memristor synapses in neuromorphic computing architectures. Nanotechnology, 24:384010, 2014. (PDF).

  • [29] G. M. Hoerzer, R. Legenstein, and Wolfgang Maass. Emergence of complex computational structures from chaotic neural networks through reward-modulated Hebbian learning. Cerebral Cortex, 24:677-690, 2014. (PDF). (Supplementary material PDF)

  • [28] R. Legenstein and W. Maass. Branch-specific plasticity enables self-organization of nonlinear computation in single neurons. The Journal of Neuroscience, 31(30):10787-10802, 2011. (PDF). (Commentary by R. P. Costa and P. J. Sjöström in Frontiers in Synaptic Neuroscience PDF)

  • [27] R. Legenstein, N. Wilbert, and L. Wiskott. Reinforcement learning on slow features of high-dimensional input streams. PLoS Computational Biology, 6(8):e1000894, 2010. (PDF).

  • [26] M. Jahrer, A. Töscher, and R. Legenstein. Combining predictions for accurate recommender systems. In KDD '10: Proceedings of the 16th ACM SIGKDD international conference on Knowledge discovery and data mining, pages 693-702, New York, NY, USA, 2010. ACM. (PDF).

  • [25] R. Legenstein, S. M. Chase, A. B. Schwartz, and W. Maass. A reward-modulated Hebbian learning rule can explain experimentally observed network reorganization in a brain control task. The Journal of Neuroscience, 30(25):8400-8410, 2010. (PDF).

  • [24] R. Legenstein, S. A. Chase, A. B. Schwartz, and W. Maass. Functional network reorganization in motor cortex can be explained by reward-modulated Hebbian learning. In Proc. of NIPS 2009: Advances in Neural Information Processing Systems, D. Koller, D. Schuurmans, Y. Bengio, and L. Bottou, editors, volume 22, pages 1105-1113. MIT Press, 2010. (PDF).

  • [23] L. Buesing, B. Schrauwen, and R. Legenstein. Connectivity, dynamics, and memory in reservoir computing with binary and analog neurons. Neural Computation, 22(5):1272-1311, 2010. (PDF).

  • [22] B. Schrauwen, L. Buesing, and R. Legenstein. On computational power and the order-chaos phase transition in reservoir computing. In Proc. of NIPS 2008, Advances in Neural Information Processing Systems, volume 21, pages 1425-1432. MIT Press, 2009. (PDF).

  • [22b] B. Schrauwen, L. Buesing, and R. Legenstein. Supplementary material to: On computational power and the order-chaos phase transition in reservoir computing. In Proc. of NIPS 2008, Advances in Neural Information Processing Systems, volume 21. MIT Press, 2009. in press. (PDF).

  • [21] Andreas Toescher, Michael Jahrer, and Robert Legenstein. Improved neighborhood-based algorithms for large-scale recommender systems. In KDD-Cup and Workshop. ACM, 2008. (PDF).

  • [20] R. Legenstein, D. Pecevski, and W. Maass. A learning theory for reward-modulated spike-timing-dependent plasticity with application to biofeedback. PLoS Computational Biology, 4(10):e1000180, 2008. (Journal link to the PDF)

  • [19] R. Legenstein, D. Pecevski, and W. Maass. Theoretical analysis of learning with reward-modulated spike-timing-dependent plasticity. In Proc. of NIPS 2007, Advances in Neural Information Processing Systems, volume 20, pages 881-888. MIT Press, 2008. (PDF).

  • [18] S. Klampfl, R. Legenstein, and W. Maass. Spiking neurons can learn to solve information bottleneck problems and extract independent components. Neural Computation, 21(4):911-959, 2009. (PDF).

  • [17] R. Legenstein and W. Maass. On the classification capability of sign-constrained perceptrons. Neural Computation, 20(1):288-309, 2008. (PDF).

  • [16] S. Klampfl, R. Legenstein, and W. Maass. Information bottleneck optimization and independent component extraction with spiking neurons. In Proc. of NIPS 2006, Advances in Neural Information Processing Systems, volume 19, pages 713-720. MIT Press, 2007. (PDF).

  • [15] R. Legenstein and W. Maass. Edge of chaos and prediction of computational performance for neural circuit models. Neural Networks, 20(3):323-334, 2007. (PDF).

  • [14] R. Legenstein and W. Maass. What makes a dynamical system computationally powerful? In New Directions in Statistical Signal Processing: From Systems to Brains, S. Haykin, J. C. Principe, T.J. Sejnowski, and J.G. McWhirter, editors, pages 127-154. MIT Press, 2007. (PDF).

  • [13] R. Legenstein, C. Naeger, and W. Maass. What can a neuron learn with spike-timing-dependent plasticity? Neural Computation, 17(11):2337-2382, 2005. (PDF).

  • [13a] R. Legenstein and W. Maass. Additional material to the paper: What can a neuron learn with spike-timing-dependent plasticity? Technical report, Institute for Theoretical Computer Science, Graz University of Technology, 2004. . (PDF)

  • [12] R. Legenstein and W. Maass. A criterion for the convergence of learning with spike timing dependent plasticity. In Advances in Neural Information Processing Systems, Y. Weiss, B. Schoelkopf, and J. Platt, editors, volume 18, pages 763-770. MIT Press, 2006. (PDF).

  • [11] T. Natschlaeger, N. Bertschinger, and R. Legenstein. At the edge of chaos: Real-time computations and self-organized criticality in recurrent neural networks. In Advances in Neural Information Processing Systems 17, Lawrence K. Saul, Yair Weiss, and Léon Bottou, editors, pages 145-152. MIT Press, Cambridge, MA, 2005. (PDF).

  • [10] W. Maass, R. Legenstein, and N. Bertschinger. Methods for estimating the computational power and generalization capability of neural microcircuits. In Advances in Neural Information Processing Systems, L. K. Saul, Y. Weiss, and L. Bottou, editors, volume 17, pages 865-872. MIT Press, 2005. (PDF).

  • [9] R. A. Legenstein and W. Maass. Wire length as a circuit complexity measure. Journal of Computer and System Sciences, 70:53-72, 2005. (PDF).

  • [8] R. Legenstein, H. Markram, and W. Maass. Input prediction and autonomous movement analysis in recurrent circuits of spiking neurons. Reviews in the Neurosciences (Special Issue on Neuroinformatics of Neural and Artificial Computation), 14(1-2):5-19, 2003. (PDF).

  • [7] W. Maass, R. Legenstein, and H. Markram. A new approach towards vision suggested by biologically realistic neural microcircuit models. In Biologically Motivated Computer Vision. Proc. of the Second International Workshop, BMCV 2002, Tuebingen, Germany, November 22-24, 2002, H. H. Buelthoff, S. W. Lee, T. A. Poggio, and C. Wallraven, editors, volume 2525 of Lecture Notes in Computer Science, pages 282-293. Springer (Berlin), 2002. (PDF).

  • [6] R. A. Legenstein. The Wire-Length Complexity of Neural Networks. PhD thesis, Graz University of Technology, 2002. (PostScript). (PDF).

  • [5] R. A. Legenstein and W. Maass. Neural circuits for pattern recognition with small total wire length. Theoretical Computer Science, 287:239-249, 2002. (PostScript). (PDF).

  • [4] R. A. Legenstein. On the complexity of knock-knee channel routing with 3-terminal nets. Technical Report, 2002. (PostScript).

  • [3] R. A. Legenstein and W. Maass. Optimizing the layout of a balanced tree. Technical Report, 2001. (PostScript). (PDF).

  • [2] R. A. Legenstein and W. Maass. Foundations for a circuit complexity theory of sensory processing. In Proc. of NIPS 2000, Advances in Neural Information Processing Systems, T. K. Leen, T. G. Dietterich, and V. Tresp, editors, volume 13, pages 259-265, Cambridge, 2001. MIT Press. (PostScript). (PDF). The poster presented at NIPS is available as gzipped Postscript.

  • [1] R. A. Legenstein. Effizientes Layout von Neuronalen Netzen. Master's thesis, Technische Universitaet Graz, September 1999. (PostScript).

  • [-] R. Legenstein, S. A. Chase, A. B. Schwartz, and W. Maass. A model for learning effects in motor cortex that may facilitate the brain control of neuroprosthetic devices. 38th Annual Conference of the Society for Neuroscience, Program 517.6, 2008.

  • [-] R. Legenstein and W. Maass. An integrated learning rule for branch strength potentiation and STDP. 39th Annual Conference of the Society for Neuroscience, Program 895.20, Poster HH36, 2009.


Zeno Jonke, Robert Legenstein, Stefan Habenschuss and Wolfgang Maass Feedback Inhibition Shapes Emergent Computational Properties of Cortical Microcircuit Motifs The journal of neuroscience 37, 8511– 8523, 2017 , Link
Christoph Pokorny, Matias Ison, Robert Legenstein and Wolfgang Maass A model for the formation of associations between memory items in the brain
Guillaume Bellec, David Kappel, Wolfgang Maass and Robert Legenstein Deep Rewiring arXiv.org e-Print archive , 2017 , Link
Christoph Pokorny, Matias Ison, Arjun Rao, Robert Legenstein, Christos H. Papadimitriou and Wolfgang Maass Associations between memory traces emerge in a generic neural circuit model through STDP bioRxiv - the Preprint Server for Biology , 1-36, 2017 , DOI , Link
David Kappel, Robert Legenstein, Stefan Habenschuss, Michael Hsieh and Wolfgang Maass Reward-based stochastic self-configuration of neural circuits arXiv.org e-Print archive arXiv preprint arXiv:1704.04238, 2017 , Link
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 and Karlheinz Meier Pattern representation and recognition with accelerated analog neuromorphic systems arXiv.org e-Print archive preprint arXiv:1703.06043, 2017
Sebastian Schmitt, Johann Klähn, Guillaume Emmanuel Fernand Bellec, Andreas Grübl, Güttler Maurice, Andreas Hartl, Stephan Hartmann, Dan Husmann, Kai Husmann, Sebastian Jeltsch, Vitali Karasenko, Mitja Kleider, Christoph Koke, Alexander Kononov, Christian Mauch, Eric Müller, Paul Müller, Johannes Partzsch, Mihai Petrovici, Stefan Schiefer, Stefan Scholze, Vasilis Thanasoulis, Bernhard Vogginger, Robert Legenstein, Wolfgang Maass, Christian Mayr, Rene Schüffny, Johannes Schemmel and Karlheinz Meier Neuromorphic Hardware In The Loop: Training a Deep Spiking Network on the BrainScaleS Wafer-Scale System arXiv.org e-Print archive arXiv:1703.01909, 2017
Robert Legenstein, Zeno Jonke, Stefan Habenschuss and Wolfgang Maass A probabilistic model for learning in cortical microcircuit motifs with data-based divisive inhibition arXiv.org e-Print archive , 1-27, 2017 , DOI
Alexander Serb, Johannes Bill, Ali Khiat, Radu Berdan, Robert Legenstein and Themis Prodromakis Unsupervised learning in probabilistic neural networks with multi-state metal-oxide memristive synapses Nature Communications , Nature Communications, Nature Communications, Nature Communications, Nature Communications, Nature Communications 7, 2016
Robert Legenstein, Christos H. Papadimitriou, Santosh Vempala and Wolfgang Maass Assembly pointers for variable binding in networks of spiking neurons arXiv.org e-Print archive preprint arXiv:1611.03698, 2016
Zhaofei Yu, David Kappel, Robert Legenstein, Sen Song, Feng Chen and Wolfgang Maass Hamiltonian synaptic sampling in a model for reward-gated network plasticity arXiv.org e-Print archive , 2016 , Link
Behnam Taraghi, Anna Saranti, Robert Legenstein and Martin Ebner Bayesian modelling of student misconceptions in the one-digit multiplication with probabilistic programming
David Kappel, Stefan Habenschuss, Robert Legenstein and Wolfgang Maass Synaptic sampling: A Bayesian approach to neural network plasticity and rewiringSynaptic sampling: A Bayesian approach to neural network plasticity and rewiring
David Kappel, Stefan Habenschuss, Robert Legenstein and Wolfgang Maass Synaptic Plasticity as Bayesian Inference
Wolfgang Maass, David Kappel, Stefan Habenschuss and Robert Legenstein Reward-based network plasticity as Bayesian inference
Johannes Bill, Lars Holger Büsing, Stefan Habenschuss, Bernhard Nessler, Wolfgang Maass and Robert Legenstein Distributed Bayesian computation and self-organized learning in sheets of spiking neurons with local lateral inhibition PLoS ONE 10, e0134356-e0134356, 2015
David Kappel, Stefan Habenschuss, Robert Legenstein and Wolfgang Maass Network plasticity as Bayesian inference PLoS computational biology 11, e1004485-e1004485, 2015
Robert Legenstein Nanoscale connections for brain-like circuits Nature (London) 521, 37-38, 2015
Christoph Pokorny, Gernot Griesbacher, Zeno Jonke and Robert Legenstein Neural Computation with Assemblies and Assembly Sequences
Robert Legenstein, David Kappel, Stefan Habenschuss and Wolfgang Maass Stochastic network plasticity as Bayesian inference
Robert Legenstein and Wolfgang Maass Ensembles of spiking neurons with noise support optimal probabilistic inference in a dynamically changing environment PLoS computational biology 10, 1-27, 2014 , DOI
Johannes Bill and Robert Legenstein A compound memristive synapse model for statistical learning through STDP in spiking neural networks Frontiers in neuroscience 8, 1-18, 2014
Robert Legenstein A comparison of manual neuronal reconstruction from biocytin histology or 2-photon imaging: morphometry and computer modeling Frontiers in Neuroanatomy 8, 65-65, 2014
Robert Legenstein Recurrent network models, reservoir computingRecurrent network models, reservoir computing1-5
Gregor Michael Hörzer, Robert Legenstein and Wolfgang Maass Emergence of complex computational structures from chaotic neural networks through reward-modulated Hebbian learning Cerebral cortex 24, 677-690, 2014 , DOI
Johannes Bill, Lars Buesing, Stefan Habenschuss, Bernhard Nessler, Robert Legenstein and Wolfgang Maass Local inhibition facilitates synaptic learning in spatially extended Bayesian spiking networks
Giacomo Indiveri, Bernabé Linares-Barranco, Robert Legenstein, George Deligeorgis and Themistoklis Prodromakis Integration of nanoscale memristor synapses in neuromorphic computing architectures Nanotechnology 24, 384010-384010, 2013 , DOI
Zeno Jonke, Stefan Habenschuss, Robert Legenstein and Wolfgang Maass Improved feature extraction by pyramidal cells through relaxed lateral inhibition
Robert Legenstein and Wolfgang Maass Spikes as temporal beliefs and the optimal temporal integration of uncertain information in networks of spiking neurons
Robert Legenstein, Dejan Pecevski, Lars Holger Büsing and Wolfgang Maass Dendritic computation could support probabilistic inference in networks of spiking neurons
Robert Legenstein and Wolfgang Maass Self-organization of nonlinear neural computation through synaptic plasticity in dendritic branches
Robert Legenstein Dendritic computation could support probabilistic inference in networks of spiking neuronsDendritic computation could support probabilistic inference in networks of spiking neurons1-1
Gregor Michael Hörzer, Robert Legenstein and Wolfgang Maass Eliminating the teacher in reservoir computingEliminating the teacher in reservoir computing32-32
Robert Legenstein and Wolfgang Maass Branch-specific plasticity enables self-organization of nonlinear computation in single neurons The journal of neuroscience 31, 10787-10802, 2011
Robert Legenstein, Steven Chase, Andrew B. Schwartz and Wolfgang Maass A reward-modulated Hebbian learning rule can explain experimentally observed network reorganization in a brain control task The journal of neuroscience 30, 8400-8410, 2010
Robert Legenstein Reinforcement learning on slow features of high-dimensional input streams PLoS computational biology 6, e1000894-e1000894, 2010
Lars Holger Büsing, Benjamin Schrauwen and Robert Legenstein Connectivity, Dynamics, and Memory in Reservoir Computing with Binary and Analog Neurons Neural computation 22, 1272-1311, 2010 , DOI
Robert Legenstein, Steven Chase, Andrew B. Schwartz and Wolfgang Maass Functional network reorganization in motor cortex can be explained by reward-modulated Hebbian learningFunctional network reorganization in motor cortex can be explained by reward-modulated Hebbian learning1105-1113
Robert Legenstein Combining predictions for accurate recommender systemsCombining predictions for accurate recommender systems693-702
Niko Wilbert, Mathias Franzius, Robert Legenstein and Laurenz Wiskott Reinforcement learning on complex visual stimuli
Robert Legenstein Computation and Learning in Neural Systems
Niko Wilbert, Robert Legenstein and Laurenz Wiskott Slowness in hierarchical networks for visual processing
Benjamin Schrauwen, Lars Holger Büsing and Robert Legenstein On Computational Power and the Order-Chaos Phase Transition in Reservoir ComputingOn Computational Power and the Order-Chaos Phase Transition in Reservoir Computing
Robert Legenstein, Steven M. Chase, Andrew B. Schwartz and Wolfgang Maass Functional network reorganization in motor cortex can be explained by reward-modulated Hebbian learning
Robert Legenstein and Wolfgang Maass An integrated learning rule for branch strength potentiation and STDP
Stefan Klampfl, Robert Albin Legenstein and Wolfgang Maass Spiking neurons can learn to solve information bottleneck problems and to extract independent components Neural computation 21, 911-959, 2009
Robert Legenstein, Dejan Pecevski and Wolfgang Maass A learning theory for reward-modulated spike-timing-dependent plasticity with application to biofeedback PLoS computational biology 4, 1-27, 2008
Robert Legenstein On Computational Power and the Order-Chaos Phase Transition in Reservoir Computing
Robert Albin Legenstein, Dejan Pecevski and Wolfgang Maass Theoretical analysis of learning with reward-modulated spike-timing-dependent plasticityTheoretical analysis of learning with reward-modulated spike-timing-dependent plasticity
Robert Albin Legenstein and Wolfgang Maass On the classification capability of sign-constrained perceptrons Neural computation 20, 208-309, 2008
Robert Legenstein, Steven M. Chase, Andrew B. Schwartz and Wolfgang Maass A model for learning effects in motor cortex that may facilitate the brain control of neuroprosthetic devicesA model for learning effects in motor cortex that may facilitate the brain control of neuroprosthetic devices
Robert Legenstein Improved neighborhood-based algorithms for large-scale recommender systemsImproved neighborhood-based algorithms for large-scale recommender systems
Robert Albin Legenstein and Wolfgang Maass What makes a dynamical system computationally powerful?What makes a dynamical system computationally powerful?127-154
Stefan Klampfl, Robert Albin Legenstein and Wolfgang Maass Information Bottleneck Optimization and Independent Component Extraction with Spiking NeuronsInformation Bottleneck Optimization and Independent Component Extraction with Spiking Neurons713-720
Robert Albin Legenstein Theoretical analysis of learning with reward-modulated spike-timing-dependent plasticity
Robert Albin Legenstein and Wolfgang Maass Edge of Chaos and Prediction of Computational Performance for Neural Circuit Models Neural networks 20, 323-333, 2007
Stefan Klampfl, Robert Albin Legenstein and Wolfgang Maass Information Bottleneck Optimization and Independent Component Extraction with Spiking Neurons
Stefan Klampfl, Robert Albin Legenstein and Wolfgang Maass Extracting Independent Components with Spiking Neurons
Robert Albin Legenstein and Wolfgang Maass A criterion for the convergence of learning with spike timing dependent plasticityA criterion for the convergence of learning with spike timing dependent plasticity763-770
Robert Albin Legenstein Analysis of Neural Microcircuits on the Systems Level
Robert Albin Legenstein and Wolfgang Maass Wire length as a circuit complexity measure Journal of computer and system sciences 70, 53-72, 2005
Robert Albin Legenstein, Christian Näger and Wolfgang Maass What can a neuron learn with spike-timing-dependent plasticity? Neural computation 17, 2337-2382, 2005
Robert Albin Legenstein Real-time computations and self organized criticality in recurrent neural networks
Thomas Natschläger, Nils Bertschinger and Robert Albin Legenstein At the edge of chaos: Real-time computations and self-organized criticality in recurrent neural networksAt the edge of chaos: Real-time computations and self-organized criticality in recurrent neural networks145-152
Robert Albin Legenstein A criterion for the convergence of learning with spike timing dependent plasticity
Wolfgang Maass, Robert Albin Legenstein and Nils Bertschinger Methods for estimating the computational power and generalization capability of neural microcircuitsMethods for estimating the computational power and generalization capability of neural microcircuits865-872
Robert Albin Legenstein Methods of Estimating the Computational Power and Generalization Capability of Neural Microcircuits
Robert Albin Legenstein, Henry Markram and Wolfgang Maass Input prediction and autonomous movement analysis in recurrent circuit of spiking neurons Reviews in the neurosciences 14, 5-19, 2003
Robert Albin Legenstein The wire-length complexity of neural networks
Robert Albin Legenstein Effizientes Layout von Neuronalen Netzen
Contact
image/svg+xml

Dr. Robert Legenstein
Institute for Theoretical Computer Science
Inffeldgasse 16b/I
8010 Graz
Austria

+43 / 316 873 5824
robert.legensteinnoSpam@igi.tugraz.at