Robert Legenstein
Robert Legenstein
Institute for Theoretical Computer Science, Graz University of Technology
Verified email at igi.tugraz.at - Homepage
TitleCited byYear
Integration of nanoscale memristor synapses in neuromorphic computing architectures
G Indiveri, B Linares-Barranco, R Legenstein, G Deligeorgis, ...
Nanotechnology 24 (38), 384010, 2013
3232013
Edge of chaos and prediction of computational performance for neural circuit models
R Legenstein, W Maass
Neural Networks 20 (3), 323-334, 2007
2932007
Combining predictions for accurate recommender systems
M Jahrer, A Töscher, R Legenstein
Proceedings of the 16th ACM SIGKDD international conference on Knowledge …, 2010
2502010
What can a neuron learn with spike-timing-dependent plasticity?
R Legenstein, C Naeger, W Maass
Neural computation 17 (11), 2337-2382, 2005
2262005
A learning theory for reward-modulated spike-timing-dependent plasticity with application to biofeedback
R Legenstein, D Pecevski, W Maass
PLoS computational biology 4 (10), e1000180, 2008
2052008
Unsupervised learning in probabilistic neural networks with multi-state metal-oxide memristive synapses
A Serb, J Bill, A Khiat, R Berdan, R Legenstein, T Prodromakis
Nature communications 7, 12611, 2016
1262016
Connectivity, dynamics, and memory in reservoir computing with binary and analog neurons
L Büsing, B Schrauwen, R Legenstein
Neural computation 22 (5), 1272-1311, 2010
1172010
Emergence of complex computational structures from chaotic neural networks through reward-modulated Hebbian learning
GM Hoerzer, R Legenstein, W Maass
Cerebral cortex 24 (3), 677-690, 2012
1042012
Branch-specific plasticity enables self-organization of nonlinear computation in single neurons
R Legenstein, W Maass
Journal of Neuroscience 31 (30), 10787-10802, 2011
1042011
A reward-modulated hebbian learning rule can explain experimentally observed network reorganization in a brain control task
R Legenstein, SM Chase, AB Schwartz, W Maass
Journal of Neuroscience 30 (25), 8400-8410, 2010
972010
What makes a dynamical system computationally powerful
R Legenstein, W Maass
New directions in statistical signal processing: From systems to brain, 127-154, 2007
942007
What makes a dynamical system computationally powerful
R Legenstein, W Maass
New directions in statistical signal processing: From systems to brain, 127-154, 2007
942007
Reinforcement learning on slow features of high-dimensional input streams
R Legenstein, N Wilbert, L Wiskott
PLoS computational biology 6 (8), e1000894, 2010
882010
A compound memristive synapse model for statistical learning through STDP in spiking neural networks
J Bill, R Legenstein
Frontiers in neuroscience 8, 412, 2014
722014
At the edge of chaos: Real-time computations and self-organized criticality in recurrent neural networks
N Bertschinger, T Natschläger, RA Legenstein
Advances in neural information processing systems, 145-152, 2005
662005
A new approach towards vision suggested by biologically realistic neural microcircuit models
W Maass, R Legenstein, H Markram
International Workshop on Biologically Motivated Computer Vision, 282-293, 2002
612002
Improved neighborhood-based algorithms for large-scale recommender systems
A Töscher, M Jahrer, R Legenstein
Proceedings of the 2nd KDD Workshop on Large-Scale Recommender Systems and …, 2008
582008
Network plasticity as Bayesian inference
D Kappel, S Habenschuss, R Legenstein, W Maass
PLoS computational biology 11 (11), e1004485, 2015
532015
On computational power and the order-chaos phase transition in reservoir computing
B Schrauwen, L Büsing, RA Legenstein
Advances in Neural Information Processing Systems, 1425-1432, 2009
482009
Input prediction and autonomous movement analysis in recurrent circuits of spikitfg neurons
R Legenstein, Η Markram, W Maass
Reviews in the Neurosciences 14 (1-2), 5-20, 2003
482003
The system can't perform the operation now. Try again later.
Articles 1–20