W. Maass

发表

Eecient Learning with Virtual Threshold Gates

W. Maass, Manfred K. Warmuthy, 1997 .

A Comparison of the Computational Power of Sigmoid and Boolean Threshold Circuits

Eduardo Sontag, W. Maass, G. Schnitger, 1994 .

What makes a dynamical system computationally powerful ?

W. Maass, R. Legenstein, 2022 .

State-dependent computations: spatiotemporal processing in cortical networks

W. Maass, D. Buonomano, 2009, Nature Reviews Neuroscience.

Coding and learning of behavioral sequences

H. Markram, W. Gerstner, W. Maass, 2004, Trends in Neurosciences.

Agnostic PAC Learning of Functions on Analog Neural Nets

Wolfgang Maass, W. Maass, 1993, Neural Computation.

Efficient Learning With Virtual Threshold Gates

Manfred K. Warmuth, Wolfgang Maass, W. Maass, 1995, Inf. Comput..

Combinatorial lower bound arguments for deterministic and nondeterministic Turing machines

W. Maass, 1985 .

Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations

Henry Markram, Wolfgang Maass, Thomas Natschläger, 2002, Neural Computation.

The p-Delta Learning Rule for Parallel Perceptrons

P. Auer, W. Maass, H. Burgsteiner, .

On-line learning with an oblivious environment and the power of randomization

Wolfgang Maass, W. Maass, 1991, COLT '91.

Distributed Fading Memory for Stimulus Properties in the Primary Visual Cortex

W. Singer, W. Maass, D. Nikolic, 2009, PLoS biology.

Threshold circuits of bounded depth

Pavel Pudlák, Wolfgang Maass, Mario Szegedy, 1987, 28th Annual Symposium on Foundations of Computer Science (sfcs 1987).

On the complexity of learning from counterexamples

Wolfgang Maass, György Turán, W. Maass, 1989, 30th Annual Symposium on Foundations of Computer Science.

On minimal pairs and minimal degrees in higher recursion theory

Wolfgang Maass, W. Maass, 1977, Arch. Math. Log..

Inadmissibility, tame R.E. sets and the admissible collapse

W. Maass, 1978 .

On the computational power of sigmoid versus Boolean threshold circuits

Georg Schnitger, Eduardo D. Sontag, Wolfgang Maass, 1991, [1991] Proceedings 32nd Annual Symposium of Foundations of Computer Science.

Neural Nets with Superlinear VC-Dimension

Wolfgang Maass, W. Maass, 1994, Neural Computation.

E?cient Temporal Processing with Biolog-ically Realistic Dynamic Synapses

Wolfgang Maass, Anthony M. Zador, Thomas Natschläger, 2001 .

Threshold circuits of bounded depth

Pavel Pudlák, Wolfgang Maass, Mario Szegedy, 1987, 28th Annual Symposium on Foundations of Computer Science (sfcs 1987).

Computational Aspects of Feedback in Neural Circuits

Eduardo D. Sontag, Wolfgang Maass, Prashant Joshi, 2006, PLoS Comput. Biol..

A Learning Theory for Reward-Modulated Spike-Timing-Dependent Plasticity with Application to Biofeedback

Robert A. Legenstein, Wolfgang Maass, Dejan Pecevski, 2008, PLoS Comput. Biol..

Inferring spike trains from local field potentials.

Arthur Gretton, Nikos K Logothetis, Wolfgang Maass, 2008, Journal of neurophysiology.

Vapnik-Chervonenkis dimension of neural nets

Peter L. Bartlett, Wolfgang Maass, P. Bartlett, 2003 .

Spiking Neurons Can Learn to Solve Information Bottleneck Problems and Extract Independent Components

Robert A. Legenstein, Wolfgang Maass, Stefan Klampfl, 2009, Neural Computation.

Special issue on echo state networks and liquid state machines

José Carlos Príncipe, Wolfgang Maass, Herbert Jaeger, 2007, Neural Networks.

On the Computational Power of Winner-Take-All

Wolfgang Maass, W. Maass, 2000, Neural Computation.

Emergence of complex computational structures from chaotic neural networks through reward-modulated Hebbian learning.

Wolfgang Maass, Robert Legenstein, Gregor M Hoerzer, 2014, Cerebral cortex.

On the complexity of learning on neural nets

Wolfgang Maass, W. Maass, 1994, EuroCOLT.

On the complexity of learning from counterexamples

W. Maass, György Turán, 1989, 30th Annual Symposium on Foundations of Computer Science.

How fast can a threshold gate learn

Wolfgang Maass, György Turán, W. Maass, 1994, COLT 1994.

Perspectives of Current Research about the Complexity of Learning on Neural Nets

Wolfgang Maass, W. Maass, 1994 .

On the Complexity of Learning From Counterexamples (extended abstract )

W. Maass, György Turán, 1989, FOCS 1989.

Emergence of Dynamic Memory Traces in Cortical Microcircuit Models through STDP

Wolfgang Maass, Stefan Klampfl, W. Maass, 2013, The Journal of Neuroscience.

Self-tuning of neural circuits through short-term synaptic plasticity.

W. Maass, David Sussillo, T. Toyoizumi, 2007, Journal of neurophysiology.

A quantitative analysis of information about past and present stimuli encoded by spikes of A1 neurons.

W. Maass, S. David, S. Shamma, 2012, Journal of neurophysiology.

Bounds for the computational power and learning complexity of analog neural nets

Wolfgang Maass, W. Maass, 1993, SIAM J. Comput..

Brain computation by assemblies of neurons

Christos H. Papadimitriou, Michael Collins, Wolfgang Maass, 2019, Proceedings of the National Academy of Sciences.

What Can a Neuron Learn with Spike-Timing-Dependent Plasticity?

Robert A. Legenstein, Wolfgang Maass, Christian Naeger, 2005, Neural Computation.

On the computational power of circuits of spiking neurons

Henry Markram, Wolfgang Maass, H. Markram, 2004, J. Comput. Syst. Sci..

STDP enables spiking neurons to detect hidden causes of their inputs

Wolfgang Maass, Bernhard Nessler, Michael Pfeiffer, 2009, NIPS.

Dynamic Stochastic Synapses as Computational Units

Wolfgang Maass, Anthony M. Zador, W. Maass, 1997, Neural Computation.

Efficient temporal processing with biologically realistic dynamic synapses

W. Maass, A. Zador, T. Natschlger, 2001, Network.

On the Computational Complexity of Networks of Spiking Neurons

Wolfgang Maass, W. Maass, 1994, NIPS.

STDP Installs in Winner-Take-All Circuits an Online Approximation to Hidden Markov Model Learning

David Kappel, Wolfgang Maass, Bernhard Nessler, 2014, PLoS Comput. Biol..

2 . 1 Learning-to-Learn and Gradient-free Optimization

W. Maass, K. Meier, T. Bohnstingl, 2019 .

Supplementary materials for: A solution to the learning dilemma for recurrent networks of spiking neurons

W. Maass, R. Legenstein, Franz Scherr, 2019 .

Probing Real Sensory Worlds of Receivers with Unsupervised Clustering

W. Maass, Michael Pfeiffer, H. Römer, 2012, PloS one.

Predicting Computational Power of Neural Circuits 2 Edge of Chaos and Prediction of Computational Power for Neural Circuit Models

W. Maass, R. Legenstein, 2022 .

Recursmly Tnivartant P-recurston Theory

W. Maass, Tnivartant p-RECURSTON, 2014 .

Analog Computations on Networks of Spiking Neurons Produced as Part of the Esprit Working Group in Neural and Computational Learning, Neurocolt 8556

W. Maass, 2014 .

On learnability and predicate logic (Extended Abstract)

W. Maass, 1995 .

On the Complexity of Computing and Learning with Networks of Spiking Neurons

W. Maass, M. Schmitt, 1998 .

Principles for an Alternative Design of Movement Primitives that Uses Probabilistic Inference in Learned Graphical Models

G. Neumann, Marc Toussaint, W. Maass, 2013 .

A probabilistic model for learning in cortical microcircuit motifs with data-based divisive inhibition

Stefan Habenschuss, Wolfgang Maass, Zeno Jonke, 2017 .

Lower Bound Methods and Separation Results for On-Line Learning Models

Wolfgang Maass, György Turán, W. Maass, 2004, Machine Learning.

An E cient Implementation of Sigmoidal Neural Nets in Temporal Coding with Noisy Spiking Neurons

Wolfgang Maass, W. Maass, 1995 .

Chapter 1 Liquid State Machines : Motivation , Theory , and Applications

Wolfgang Maass, W. Maass, 2010 .

On the relationship between the complexity, the degree, and the extension of a computable set

W. Maass, T. Slaman, 1990 .

2 Computing with Spiking Neurons

W. Maass, 1999 .

N C ] 1 1 N ov 2 01 6 Assembly pointers for variable binding in networks of spiking neurons

C. Papadimitriou, S. Vempala, W. Maass, 2016 .

Foreword Neural Pulse Coding

W. Maass, C. Blshop, 1999 .

Title : Inferring spike trains from local field potentials

N. Logothetis, W. Maass, A. Gretton, 2007 .

A Learning Rule for Universal Approximators with a Single Non-Linearity

P. Auer, W. Maass, H. Burgsteiner, 2007 .

Spiking Neurons

Wolfgang Maass, W. Maass, 1998, NC.

Finding the Key to a Synapse

Wolfgang Maass, Thomas Natschläger, W. Maass, 2000, NIPS.

Results and open problems regarding the role of local feature descriptors for image classification in computer vision , and image representation in primary visual cortex

W. Maass, M. Rasch, H. Bischof, 2006 .

2021 Roadmap on Neuromorphic Computing and Engineering pdf

Gouhei Tanaka, Chiara Bartolozzi, Giacomo Indiveri, 2021, ArXiv.

On the complexity of learning from counterexamples and membership queries (abstract)

Wolfgang Maass, György Turán, W. Maass, 1990, COLT 1990.

Ups and downs in the genesis of cortical computation

Wolfgang Maass, C. M. Michel, Anders Lansner, 2006 .

Computation with spiking neurons

Wolfgang Maass, W. Maass, 2003 .

Visual Grounding of Route Descriptions in Dynamic Environments

Jörg Baus, Wolfgang Maass, Joachim Paul, 1995 .

Self-supervised learning of probabilistic prediction through synaptic plasticity in apical dendrites: A normative model

W. Maass, R. Legenstein, A. Rao, 2022, bioRxiv.

Probabilistic skeletons endow brain-like neural networks with innate computing capabilities

W. Maass, Christoph Stöckl, D. Lang, 2021 .

A Method for the Efficient Design of Boltzmann Machines for Classiffication Problems

W. Maass, Ajay Gupta, 1990, NIPS 1990.

Structure induces computational function in networks with diverse types of spiking neurons

W. Maass, Christoph Stöckl, D. Lang, 2022, bioRxiv.

Theory and Practice of Machine Learning (Dagstuhl Seminar 9702)

Thomas G. Dietterich, Hans Ulrich Simon, Wolfgang Maass, 2021 .

Theory and Praxis of Machine Learning (Dagstuhl Seminar 9426)

Thomas G. Dietterich, Hans Ulrich Simon, Manfred K. Warmuth, 2021 .

On the Relevance of the Shape of Postsynaptic Potentials for the Computational Power of Spiking Neur

Wolfgang Maass, Berthold Ruf, W. Maass, 1995 .

Vapnik-Chervonenkis dimension of neural networks

Wolfgang Maass, W. Maass, 1998 .

On the complexity of function learning

Philip M. Long, P. Auer, W. Maass, 1993, COLT '93.

V1Detailed Laminar Network Model for a Patch of Responses Stimuli in Monkey Area V1 With Simulated Statistical Comparison of Spike Responses to Natural

Nikos K. Logothetis, Wolfgang Maass, Klaus Schuch, 2011 .

Edge of Chaos and Prediction of Computational Power for Neural Microcircuit Models

Wolfgang Maass, Robert Legenstein, W. Maass, 2005 .

On the Complexity of Learning on Feedforward Neural Nets

Wolfgang Maass, W. Maass, 1993 .

Measuring Biosignals of Overweight and Obese Children for Real-Time Feedback and Predicting Performance

W. Maass, N. Öksüz, Russa Biswas, 2018 .

Introduction: Spiking Neurons in Neuroscience and Technology

Stephen Grossberg, Henry Markram, Wolfgang Maass, 2001, Neural Networks.

On the Computational Power of Recurrent Circuits of Spiking Neurons

Henry Markram, Wolfgang Maass, H. Markram, 2002, Electron. Colloquium Comput. Complex..

Total Wire Length as a Salient Circuit Complexity Measure for Sensory Processing

Robert A. Legenstein, Wolfgang Maass, W. Maass, 2001, Electron. Colloquium Comput. Complex..

two Lower Bound Arguments with "Inaccessible" Numbers

Martin Dietzfelbinger, Wolfgang Maass, W. Maass, 1986, Symposium on Computation Theory.

Structure induces computational function in networks with diverse types of spiking neurons

W. Maass, Christoph Stöckl, D. Lang, 2022, bioRxiv.

Computing with spiking neurons

Wolfgang Maass, W. Maass, 1999 .

Recurrent Neural Networks - Models, Capacities, and Applications, 20.01. - 25.01.2008

Luc De Raedt, Pascal Hitzler, Barbara Hammer, 2008, Recurrent Neural Networks.

A data-based large-scale model for primary visual cortex enables brain-like robust and versatile visual processing

W. Maass, Franz Scherr, Guozhang Chen, 2022, bioRxiv.

A Data-analytical System to Predict Therapy Success for Obese Children

Wolfgang Maass, Tobias Kowatsch, Iaroslav Shcherbatyi, 2018, ICIS.

Anatomical and neurophysiological data on primary visual cortex 1 suffice for reproducing brain-like robust multiplexing of visual 2 function

W. Maass, Franz Scherr, Guozhang Chen, 2022 .

On the Complexity of Function Learning

Philip M. Long, P. Auer, W. Maass, 1993, Machine-mediated learning.

Strong reducibilities in α- and β-recursion theory

W. Maass, Martin Dietzfelbinger, 1985 .

Splitting and Density for the Recursive Sets of a Fixed Time Complexity

W. Maass, T. Slaman, 1992 .

High α-Recursively Enumerable Degrees

W. Maass, 1978 .

Stochastic network plasticity as Bayesian inference

David Kappel, Stefan Habenschuss, Wolfgang Maass, 2015 .

Neural Computation: A Research Topic for Theoretical Computer Science? Some Thoughts and Pointers

Wolfgang Maass, W. Maass, 2001, Bull. EATCS.

Models for Fast Analog Computation with Spiking Neurons

Wolfgang Maass, W. Maass, 1998, ICONIP.

STDP performs stochastic EM to reveal the hidden causes of spatiotemporal spiking patterns

Wolfgang Maass, Michael Pfeiffer, Bernhard Nessler, 2009, NIPS 2009.

present stimuli encoded by spikes of A1 neurons A quantitative analysis of information about past and

Stephen V. David, Wolfgang Maass, Shihab A. Shamma, 2012 .

Spikes as temporal beliefs and the optimal temporal integration of uncertain information in networks of spiking neurons

Wolfgang Maass, Robert Legenstein, W. Maass, 2012 .

Spatial Layout Identification and Incremental Descriptions

Wolfgang Maass, Klaus-Peter Gapp, W. Maass, 1994 .

UPs and DOWNs in cortical computation

Eörs Szathmáry, C. M. Michel, Anders Lansner, 2006 .

Optimizing the Layout of a Balanced Tree

Robert A. Legenstein, Wolfgang Maass, W. Maass, 2001, Electron. Colloquium Comput. Complex..

Spike-based symbolic computations on symbol sequences

Wolfgang Maass, Robert Legenstein, Ceca Kraisnikovic, 2021 .

Computing and learning with dynamic synapses

Wolfgang Maass, Wolfgang Maass, Anthony M. Zador, 1999 .

Spike frequency adaptation supports network computations on temporally dispersed information

Wolfgang Maass, Robert Legenstein, Guillaume Bellec, 2020, bioRxiv.

A Solution of the Credit Assignment Problem in the Case of Learning Rectangles (Abstract)

Zhixiang Chen, Wolfgang Maass, W. Maass, 1992, Analogical and Inductive Inference.

The Complexity Types of Computable Sets (extended abstract)

Wolfgang Maass, W. Maass, 1989 .

Emergence of Optimal Decoding of Population Codes Through STDP

Stefan Habenschuss, Wolfgang Maass, Helmut Puhr, 2013, Neural Computation.

Local inhibition facilitates synaptic learning in spatially extended Bayesian spiking networks

Stefan Habenschuss, Wolfgang Maass, Lars Buesing, 2013 .

Long range coupling between V4 and PF in theta band during visual short-term memory

Wolfgang Maass, Gregor Rainer, S Liebe, 2009 .

A Hebbian Learning Rule for Optimal Decision Making

Wolfgang Maass, Michael Pfeiffer, Bernhard Nessler, 2008 .

Reward-based network plasticity as Bayesian inference

David Kappel, Stefan Habenschuss, Wolfgang Maass, 2015 .

Efficient Design of Boltzmann Machines

Wolfgang Maass, Ajay Gupta, W. Maass, 1990, NIPS.

On the relevance of time in neural computation and learning

Wolfgang Maass, W. Maass, 2001, Theor. Comput. Sci..

Group Report : Neocortical Microcircuits UPs and DOWNs in Cortical Computation

Eörs Szathmáry, C. M. Michel, Anders Lansner, 2006 .

An integrated learning rule for branch strength potentiation and STDP

Wolfgang Maass, Robert Legenstein, W. Maass, 2009 .

Review: Martin D. Davis, Elaine J. Weyuker, Computability, Complexity, and Languages. Fundamentals of Theoretical Computer Science

Wolfgang Maass, W. Maass, 1987, The Journal of Symbolic Logic.

Unsupervised Learning (Dagstuhl Seminar 99121)

Joachim M. Buhmann, Wolfgang Maass, Naftali Tishby, 2021 .

Associative Memory with Networks of Spiking Neurons in Temporal Coding

Wolfgang Maass, Thomas Natschläger, W. Maass, 1998 .

Solving Sudoku, a constraint satisfaction problem, through structured interactions between stochastically firing excitatory and inhibitory neurons.

Stefan Habenschuss, Wolfgang Maass, Zeno Jonke, 2013 .

Local prediction-learning enables neural networks to plan

W. Maass, Christoph Stöckl, 2022, bioRxiv.

OF RECURSIVELY ENUMERABLE SETS WITH SUPERSETS EFFECTIVELY ISOMORPHIC TO ALL RECURSIVELY ENUMERABLE SETS

W. Maass, 2009 .

Brain Computation: A Computer Science Perspective

Santosh S. Vempala, Christos H. Papadimitriou, Robert A. Legenstein, 2019, Computing and Software Science.

Biologically inspired alternatives to backpropagation through time for learning in recurrent neural nets pdf

Robert A. Legenstein, Wolfgang Maass, Franz Scherr, 2019, ArXiv.

STDP Forms Associations between Memory Traces in Networks of Spiking Neurons

Wolfgang Maass, Christoph Pokorny, Robert Legenstein, 2017, bioRxiv.

Inhibitory networks orchestrate the self-organization of computational function in cortical microcircuit motifs through STDP

Wolfgang Maass, Stefan Häusler, W. Maass, 2017, bioRxiv.

Associations between memory traces emerge in a generic neural circuit model through STDP

Christos H. Papadimitriou, Wolfgang Maass, Matias J. Ison, 2017 .

Learning Probabilistic Inference through Spike-Timing-Dependent Plasticity123

Wolfgang Maass, Dejan Pecevski, W. Maass, 2016, eNeuro.

Synaptic Sampling: A Bayesian Approach to Neural Network Plasticity and Rewiring

David Kappel, Robert A. Legenstein, Stefan Habenschuss, 2015, NIPS.

Network Plasticity as Bayesian Inference

David Kappel, Robert A. Legenstein, Stefan Habenschuss, 2015, PLoS Comput. Biol..

Bayesian Computation Emerges in Generic Cortical Microcircuits through Spike-Timing-Dependent Plasticity

Wolfgang Maass, Lars Buesing, Bernhard Nessler, 2013, PLoS Comput. Biol..

Branch-Specific Plasticity Enables Self-Organization of Nonlinear Computation in Single Neurons

Wolfgang Maass, Robert Legenstein, W. Maass, 2011, The Journal of Neuroscience.

A Spiking Neuron as Information Bottleneck

Wolfgang Maass, Lars Buesing, Lars Buesing, 2010, Neural Computation.

Theory of the Computational Function of Microcircuit Dynamics

Henry Markram, Wolfgang Maass, H. Markram, 2004 .

Spiking neurons and the induction of finite state machines

Wolfgang Maass, Thomas Natschläger, W. Maass, 2002, Theor. Comput. Sci..

Neural Systems as Nonlinear Filters

Eduardo D. Sontag, Wolfgang Maass, Eduardo Sontag, 2000, Neural Computation.

A Model for Fast Analog Computation Based on Unreliable Synapses

Wolfgang Maass, Thomas Natschläger, W. Maass, 2000, Neural Computation.

Fast analog computation in networks of spiking neurons using unreliable synapses

Wolfgang Maass, Thomas Natschläger, W. Maass, 1999, ESANN.

On the Role of Time and Space in Neural Computation

Wolfgang Maass, W. Maass, 1998, MFCS.

On the relevance of time in neural computation and learning

Wolfgang Maass, W. Maass, 2001, Theor. Comput. Sci..

Algorithms and lower bounds for on-line learning of geometrical concepts

W. Maass, György Turán, 2004, Machine-mediated learning.

Algorithms and Lower Bounds for On-Line Learning of Geometrical Concepts

Wolfgang Maass, György Turán, W. Maass, 1994, Machine Learning.

Computing the Maximum Bichromatic Discrepancy with Applications to Computer Graphics and Machine Learning

Dimitrios Gunopulos, David P. Dobkin, Wolfgang Maass, 1996, J. Comput. Syst. Sci..

A Theoretical Basis for Emergent Pattern Discrimination in Neural Systems Through Slow Feature Extraction

Wolfgang Maass, Stefan Klampfl, W. Maass, 2010, Neural Computation.

A New Approach towards Vision Suggested by Biologically Realistic Neural Microcircuit Models

Henry Markram, Robert A. Legenstein, Wolfgang Maass, 2002, Biologically Motivated Computer Vision.

Towards a theoretical foundation for morphological computation with compliant bodies

Helmut Hauser, Auke Jan Ijspeert, Wolfgang Maass, 2011, Biological Cybernetics.

Meanders and Their Applications in Lower Bounds Arguments

Noga Alon, Wolfgang Maass, N. Alon, 1988, J. Comput. Syst. Sci..

Lower bound methods and separation results for on-line learning models

Wolfgang Maass, György Turán, W. Maass, 1992, Machine Learning.

On the complexity of learning from counterexamples and membership queries

Wolfgang Maass, György Turán, W. Maass, 1990, Proceedings [1990] 31st Annual Symposium on Foundations of Computer Science.

On the Complexity of Learning for Spiking Neurons with Temporal Coding

Michael Schmitt, Wolfgang Maass, W. Maass, 1999, Inf. Comput..

On the complexity of learning for a spiking neuron (extended abstract)

Michael Schmitt, Wolfgang Maass, W. Maass, 1997, COLT '97.

Computing on Analog Neural Nets with Arbitrary Real Weights

Wolfgang Maass, W. Maass, 1994 .

Long Term Memory and the Densest K-Subgraph Problem

Santosh S. Vempala, Christos H. Papadimitriou, Robert A. Legenstein, 2018, ITCS.

2007 Special Issue: Edge of chaos and prediction of computational performance for neural circuit models

Robert A. Legenstein, Wolfgang Maass, W. Maass, 2007 .

Synaptic Plasticity as Bayesian Inference

W. Maass, R. Legenstein, D. Kappel, 2015 .

On the Computational Power of Neural Microcircuit Models: Pointers to the Literature

Wolfgang Maass, W. Maass, 2002, ICANN.

A Dynamic Connectome Supports the Emergence of Stable Computational Function of Neural Circuits through Reward-Based Learning

David Kappel, Stefan Habenschuss, Wolfgang Maass, 2017, eNeuro.

Neural Dynamics as Sampling: A Model for Stochastic Computation in Recurrent Networks of Spiking Neurons

Wolfgang Maass, Lars Buesing, Johannes Bill, 2011, PLoS Comput. Biol..

Belief Propagation in Networks of Spiking Neurons

Wolfgang Maass, Rodney J. Douglas, Andreas Steimer, 2009, Neural Computation.

Motif distribution, dynamical properties, and computational performance of two data-based cortical microcircuit templates

Wolfgang Maass, Klaus Schuch, Stefan Haeusler, 2009, Journal of Physiology-Paris.

Networks of Spiking Neurons: The Third Generation of Neural Network Models

Wolfgang Maass, W. Maass, 1996, Electron. Colloquium Comput. Complex..

Paradigms for Computing with Spiking Neurons

Wolfgang Maass, W. Maass, 2002 .

Statistical comparison of spike responses to natural stimuli in monkey area V1 with simulated responses of a detailed laminar network model for a patch of V1.

Nikos K Logothetis, Wolfgang Maass, Klaus Schuch, 2011, Journal of neurophysiology.

A Simple Model for Neural Computation with Firing Rates and Firing Correlations

Wolfgang Maass, W. Maass, 1998, Electron. Colloquium Comput. Complex..

From vision to multimodal communication: Incremental route descriptions

Wolfgang Maass, W. Maass, 1994, Artificial Intelligence Review.

Towards a Computational Semantics of Pathrelations

Wolfgang Maass, A. Krueger, W. Maass, 1997 .

From visual perception to multimodal communication: Incremental route descriptions

Wolfgang Maass, W. Maass, 1994 .

How Spatial Information Connects Visual Perception and Natural Language Generation in Dynamic Environments: Towards a Computational Model

W. Maass, 1995, COSIT.

Investigation of the stability of Boltzmann's collision equation by a family of Lyapunov functionals

W. Maass, 1977 .

Embodied Synaptic Plasticity With Online Reinforcement Learning

Rüdiger Dillmann, Robert A. Legenstein, Wolfgang Maass, 2019, Front. Neurorobot..

Deep Rewiring: Training very sparse deep networks pdf

David Kappel, Robert A. Legenstein, Wolfgang Maass, 2017, ICLR.

Noise as a Resource for Computation and Learning in Networks of Spiking Neurons

Wolfgang Maass, W. Maass, 2014, Proceedings of the IEEE.

Liquid State Machines: Motivation, Theory, and Applications

Wolfgang Maass, W. Maass, 2010 .

2022 roadmap on neuromorphic computing and engineering

Gouhei Tanaka, Mufti Mahmud, Chiara Bartolozzi, 2021, Neuromorph. Comput. Eng..

A solution to the learning dilemma for recurrent networks of spiking neurons

Wolfgang Maass, Franz Scherr, Robert Legenstein, 2019, Nature Communications.

Optimized spiking neurons can classify images with high accuracy through temporal coding with two spikes

Wolfgang Maass, Christoph Stockl, W. Maass, 2020, Nature Machine Intelligence.

Lower Bounds for the Computational Power of Networks of Spiking Neurons

Wolfgang Maass, W. Maass, 1996, Neural Computation.

Long short-term memory and Learning-to-learn in networks of spiking neurons pdf

Robert A. Legenstein, Wolfgang Maass, Anand Subramoney, 2018, NeurIPS.

Spike-frequency adaptation provides a long short-term memory to networks of spiking neurons

Wolfgang Maass, Robert Legenstein, Anand Subramoney, 2020 .

Spike frequency adaptation supports network computations on temporally dispersed information

W. Maass, R. Legenstein, G. Bellec, 2020, bioRxiv.

Neuromorphic Hardware Learns to Learn

Karlheinz Meier, Wolfgang Maass, Franz Scherr, 2019, Front. Neurosci..

Learned graphical models for probabilistic planning provide a new class of movement primitives

Marc Toussaint, Wolfgang Maass, Gerhard Neumann, 2013, Front. Comput. Neurosci..

CaMKII activation supports reward-based neural network optimization through Hamiltonian sampling

David Kappel, Wolfgang Maass, Sen Song, 2016 .

On the Classification Capability of Sign-Constrained Perceptrons

Robert A. Legenstein, Wolfgang Maass, W. Maass, 2008, Neural Computation.

Hebbian Learning of Bayes Optimal Decisions

Wolfgang Maass, Bernhard Nessler, Michael Pfeiffer, 2008, NIPS.

A learning rule for very simple universal approximators consisting of a single layer of perceptrons

Peter Auer, Wolfgang Maass, Harald Burgsteiner, 2008, Neural Networks.

A Statistical Analysis of Information- Processing Properties of Lamina-specific Cortical Microcircuit Models

Wolfgang Maass, Stefan Haeusler, W. Maass, 2022 .

Temporal dynamics of information content carried by neurons in the primary visual cortex

Danko Nikolic, Wolfgang Maass, Wolf Singer, 2006, NIPS.

Digital Object Memory Based Monitoring Solutions in Manufacturing Processes

Tauno Otto, Wolfgang Maass, Tanel Aruväli, 2014 .

10302 Abstracts Collection - Learning paradigms in dynamic environments

Marc Toussaint, Pascal Hitzler, Barbara Hammer, 2010, Learning paradigms in dynamic environments.

Neural Computation with Winner-Take-All as the Only Nonlinear Operation

Wolfgang Maass, W. Maass, 1999, NIPS.

Searching for principles of brain computation

Wolfgang Maass, W. Maass, 2016, Current Opinion in Behavioral Sciences.

Stochastic Computations in Cortical Microcircuit Models

Stefan Habenschuss, Wolfgang Maass, Zeno Jonke, 2013, PLoS Comput. Biol..

Online spatio-temporal learning in deep neural networks

W. Maass, E. Eleftheriou, A. Pantazi, 2020, ArXiv.

Analysis of the computational strategy of a detailed laminar cortical microcircuit model for solving the image-change-detection task

W. Maass, Franz Scherr, 2021, bioRxiv.

Fast Approximation Algorithms for a Nonconvex Covering Problem

Wolfgang Maass, Dorit S. Hochbaum, W. Maass, 1987, J. Algorithms.

Are Recursion Theoretic Arguments Useful in Complexity Theory

Wolfgang Maass, W. Maass, 1986 .

Approximation schemes for covering and packing problems in image processing and VLSI

Wolfgang Maass, Dorit S. Hochbaum, W. Maass, 1985, JACM.

Approximation Schemes for Covering and Packing Problems in Robotics and VLSI

Wolfgang Maass, Dorit S. Hochbaum, W. Maass, 1984, STACS.

Memory-Efficient Deep Learning on a SpiNNaker 2 Prototype

Steve B. Furber, David Kappel, Wolfgang Maass, 2018, Front. Neurosci..

On the Effect of Analog Noise in Discrete-Time Analog Computations

Pekka Orponen, Wolfgang Maass, W. Maass, 1996, Neural Computation.

Efficient Reward-Based Structural Plasticity on a SpiNNaker 2 Prototype

Steve B. Furber, Robert A. Legenstein, Wolfgang Maass, 2019, IEEE Transactions on Biomedical Circuits and Systems.

Neuromorphic hardware in the loop: Training a deep spiking network on the BrainScaleS wafer-scale system

Robert A. Legenstein, Wolfgang Maass, Andreas Hartel, 2017, 2017 International Joint Conference on Neural Networks (IJCNN).

The role of feedback in morphological computation with compliant bodies

Helmut Hauser, Auke Jan Ijspeert, Wolfgang Maass, 2012, Biological Cybernetics.

Probabilistic Inference in General Graphical Models through Sampling in Stochastic Networks of Spiking Neurons

Wolfgang Maass, Lars Buesing, Dejan Pecevski, 2011, PLoS Comput. Biol..

Data-based large-scale models provide a window into the organization of cortical computations

W. Maass, Franz Scherr, Guozhang Chen, 2023, bioRxiv.

Liquid Computing

Wolfgang Maass, W. Maass, 2007, CiE.

Movement Generation with Circuits of Spiking Neurons

Wolfgang Maass, Prashant Joshi, W. Maass, 2005, Neural Computation.

Movement Generation and Control with Generic Neural Microcircuits

Wolfgang Maass, Prashant Joshi, W. Maass, 2004, BioADIT.

A model for the interaction of oscillations and pattern generation with real-time computing in generic neural microcircuit models

Wolfgang Maass, Alexander Kaske, W. Maass, 2006, Neural Networks.

Methods for Estimating the Computational Power and Generalization Capability of Neural Microcircuits

Robert A. Legenstein, Wolfgang Maass, Nils Bertschinger, 2004, NIPS.

Computational models for generic cortical microcircuits

Henry Markram, Wolfgang Maass, Thomas Natschläger, 2004 .

Perspectives of the high-dimensional dynamics of neural microcircuits from the point of view of low-dimensional readouts

Henry Markram, Wolfgang Maass, Stefan Häusler, 2003, Complex..

Input Prediction and Autonomous Movement Analysis in Recurrent Circuits of Spikitfg Neurons

R. Legenstein,, Η. Markram,, W. Maass,, 2003, Reviews in the neurosciences.

Computer models and analysis tools for neural microcircuits

Henry Markram, Wolfgang Maass, Thomas Natschläger, 2003 .

Reducing Communication for Distributed Learning in Neural Networks

Peter Auer, Wolfgang Maass, Harald Burgsteiner, 2002, ICANN.

Synapses as dynamic memory buffers

Henry Markram, Wolfgang Maass, H. Markram, 2002, Neural Networks.

Analog Neural Nets with Gaussian or Other Common Noise Distributions Cannot Recognize Arbitrary Regular Languages

Eduardo D. Sontag, Wolfgang Maass, Eduardo Sontag, 1999, Neural Computation.

On-line learning of rectangles

Zhixiang Chen, Wolfgang Maass, W. Maass, 1992, COLT '92.

Motion planning among time dependent obstacles

Wolfgang Maass, Klaus Sutner, W. Maass, 1988, Acta Informatica.

ONSAGER‐CASIMIR Relations and Dynamical Optimization Principle

W. Maass, 1975 .

On the communication complexity of graph properties

Wolfgang Maass, András Hajnal, György Turán, 1988, STOC '88.

Reward-based stochastic self-configuration of neural circuits pdf

David Kappel, Robert A. Legenstein, Stefan Habenschuss, 2017, ArXiv.

12 Computing and Learning with Dynamic Synapses

Wolfgang Maass, Anthony M. Zador, W. Maass, 2022 .

Distributed Bayesian Computation and Self-Organized Learning in Sheets of Spiking Neurons with Local Lateral Inhibition

Stefan Habenschuss, Wolfgang Maass, Lars Buesing, 2015, PloS one.

Reward-Modulated Hebbian Learning of Decision Making

Wolfgang Maass, Rodney J. Douglas, Bernhard Nessler, 2010, Neural Computation.

Networks of spiking neurons can emulate arbitrary Hopfield nets in temporal coding

Wolfgang Maass, Thomas Natschläger, W. Maass, 1997 .

A Long Short-Term Memory for AI Applications in Spike-based Neuromorphic Hardware pdf

Wolfgang Maass, Andreas Wild, Arjun Rao, 2021, Nature Machine Intelligence.

Fast identification of geometric objects with membership queries

Wolfgang Maass, William J. Bultman, W. Maass, 1991, COLT '91.

Analysis of visual processing capabilities and neural coding strategies of a detailed model for laminar cortical microcircuits in mouse V1

W. Maass, Franz Scherr, Guozhang Chen, 2021 .

The "Liquid Computer": A Novel Strategy for Real-Time Computing on Time Series

Henry Markram, Wolfgang Maass, Thomas Natschläger, 2002 .

A Reward-Modulated Hebbian Learning Rule Can Explain Experimentally Observed Network Reorganization in a Brain Control Task

Wolfgang Maass, Robert Legenstein, Steven M Chase, 2010, The Journal of Neuroscience.

Current State and Future Directions for Learning in Biological Recurrent Neural Networks: A Perspective Piece

Wolfgang Maass, Claudia Clopath, Rui Ponte Costa, 2021, Neurons, Behavior, Data analysis, and Theory.

CCN GAC Workshop: Issues with learning in biological recurrent neural networks pdf

Wolfgang Maass, Claudia Clopath, Rui Ponte Costa, 2021, ArXiv.

Reservoirs learn to learn pdf

Wolfgang Maass, Franz Scherr, Anand Subramoney, 2019, Reservoir Computing.

Theory and Applications of Agnostic PAC-Learning with Small Decision Trees

Peter Auer, Wolfgang Maass, Robert C. Holte, 1995, ICML.

On the complexity of function learning

Gerhard J. Woeginger, Philip M. Long, Peter Auer, 1993, COLT '93.

Fast Sigmoidal Networks via Spiking Neurons

Wolfgang Maass, W. Maass, 1997, Neural Computation.

Feedback Inhibition Shapes Emergent Computational Properties of Cortical Microcircuit Motifs

Stefan Habenschuss, Wolfgang Maass, Zeno Jonke, 2017, The Journal of Neuroscience.

The Complexity of Matrix Transposition on One-Tape Off-Line Turing Machines

Martin Dietzfelbinger, Wolfgang Maass, W. Maass, 1988, Theor. Comput. Sci..

Efficient agnostic PAC-learning with simple hypothesis

Wolfgang Maass, W. Maass, 1994, COLT '94.

Quadratic lower bounds for deterministic and nondeterministic one-tape turing machines

Wolfgang Maass, W. Maass, 1984, STOC '84.

Wire length as a circuit complexity measure

Robert A. Legenstein, Wolfgang Maass, W. Maass, 2005, J. Comput. Syst. Sci..

Foundations for a Circuit Complexity Theory of Sensory Processing

Robert A. Legenstein, Wolfgang Maass, W. Maass, 2000, NIPS.

The complexity types of computable sets

Wolfgang Maass, Theodore A. Slaman, W. Maass, 1989, [1989] Proceedings. Structure in Complexity Theory Fourth Annual Conference.

To Spike or Not to Spike: That Is the Question

Wolfgang Maass, W. Maass, 2015, Proc. IEEE.

Noisy Spiking Neurons with Temporal Coding have more Computational Power than Sigmoidal Neurons

Wolfgang Maass, W. Maass, 1996, NIPS.

On the Computational Power of Noisy Spiking Neurons

Wolfgang Maass, W. Maass, 1995, NIPS.

Hamiltonian synaptic sampling in a model for reward-gated network plasticity pdf

David Kappel, Robert A. Legenstein, Wolfgang Maass, 2016, ArXiv.

One-shot learning with spiking neural networks

Wolfgang Maass, Franz Scherr, Christoph Stöckl, 2020, bioRxiv.

Ensembles of Spiking Neurons with Noise Support Optimal Probabilistic Inference in a Dynamically Changing Environment

Robert A. Legenstein, Wolfgang Maass, W. Maass, 2014, PLoS Comput. Biol..

Local prediction-learning in high-dimensional spaces enables neural networks to plan

W. Maass, Christoph Stöckl, Yukun Yang, 2023, bioRxiv.

Fading memory and kernel properties of generic cortical microcircuit models

Henry Markram, Wolfgang Maass, Thomas Natschläger, 2004, Journal of Physiology-Paris.

On the stability of motion of a radiating electron

W. Maass, J. Petzold, 1978 .

Learning complex motions by sequencing simpler motion templates

Jan Peters, Wolfgang Maass, Gerhard Neumann, 2009, ICML '09.

Efficient Continuous-Time Reinforcement Learning with Adaptive State Graphs

Wolfgang Maass, Gerhard Neumann, Michael Pfeiffer, 2007, ECML.

A Model for Real-Time Computation in Generic Neural Microcircuits

Henry Markram, Wolfgang Maass, Thomas Natschläger, 2002, NIPS.

Compensating Inhomogeneities of Neuromorphic VLSI Devices Via Short-Term Synaptic Plasticity

Johannes Schemmel, Karlheinz Meier, Wolfgang Maass, 2010, Front. Comput. Neurosci..

Functional network reorganization in motor cortex can be explained by reward-modulated Hebbian learning

Robert A. Legenstein, Wolfgang Maass, Steven M. Chase, 2009, NIPS.

Biologically inspired kinematic synergies enable linear balance control of a humanoid robot

Helmut Hauser, Auke Jan Ijspeert, Wolfgang Maass, 2011, Biological Cybernetics.

From Mental Models to Machine Learning Models via Conceptual Models

Veda C. Storey, Roman Lukyanenko, Wolfgang Maass, 2021, BPMDS/EMMSAD@CAiSE.

Solving Constraint Satisfaction Problems with Networks of Spiking Neurons

Stefan Habenschuss, Wolfgang Maass, Zeno Jonke, 2016, Front. Neurosci..

On the stability of a class of kinetic equations

W. Maass, 1983 .

A Calculus for Brain Computation

Christos H. Papadimitriou, Wolfgang Maass, Santosh Vempala, 2019, 2019 Conference on Cognitive Computational Neuroscience.

Electronic Colloquium on Computational Complexity Agnostic Pac-learning of Functions on Analog Neural Nets

W. Maass, 2022 .

Assembly pointers for variable binding in networks of spiking neurons

Christos H. Papadimitriou, Wolfgang Maass, Robert Legenstein, 2016 .

State-dependent computations: spatiotemporal processing in cortical networks

W. Maass, D. Buonomano, 2009, Nature Reviews Neuroscience.

Competition between bottom-up visual input and internal inhibition generates error neurons in a model of the mouse primary visual cortex

W. Maass, C. Mirasso, J. Ramasco, 2023, bioRxiv.

On Computations with Pulses

Wolfgang Maass, Berthold Ruf, W. Maass, 1999, Inf. Comput..

Emulation of Hopfield networks with spiking neurons in temporal coding

Wolfgang Maass, Thomas Natscläger, W. Maass, 1998 .

The Computational Power of Spiking Neurons Depends on the Shape of the Postsynaptic Potentials

Wolfgang Maass, Berthold Ruf, W. Maass, 1996, Electron. Colloquium Comput. Complex..

On the Effect of Analog Noise in Discrete-Time Analog Computations

W. Maass, P. Orponen, 1996, Neural Computation.

A Reward-Modulated Hebbian Learning Rule Can Explain Experimentally Observed Network Reorganization in a Brain Control Task

A. Schwartz, W. Maass, R. Legenstein, 2010, The Journal of Neuroscience.

Automated Learning of User Preferences for Selection of High Quality 3D Designs

Wolfgang Maass, Prashant Bhat, Iaroslav Shcherbatyi, 2019, Procedia CIRP.

Smoothed Analysis of Discrete Tensor Decomposition and Assemblies of Neurons

Santosh S. Vempala, Amin Saberi, Christos H. Papadimitriou, 2018, NeurIPS.

A model for fast analog computations with noisy spiking neurons

Wolfgang Maass, W. Maass, 1997 .

Fast Sigmoidal N etworks v ia Spiking Neurons

Wolfgang Maass, W. Maass, 1997 .

On the Stability Behaviour of Boltzmann's Equation

W. Maass, 1970 .

On a- and -recursively enumerable degrees

W. Maass, 1979 .

The uniform regular set theorem in α-recursion theory

Wolfgang Maass, W. Maass, 1978, Journal of Symbolic Logic.

Annals of Mathematical Logic 16 Lj9'19) 205-231 @ North-holland Publishing Cornpany on C-and P-recursmly Enumerable Degrees a Few Years Ago

W. Maass, 2014 .

Edge of chaos and prediction of computational performance for neural circuit models

W. Maass, R. Legenstein, 2007, Neural Networks.

Moving Populations Event Recognition Under Re-Identification and Data Locality Constraints

Wolfgang Maaß, Tom Michels, W. Maass, 2015, Wirtschaftsinformatik.

Fine structure theory of the constructible universe in α- and β-recursion theory

W. Maass, 1978 .

A theoretical basis for efficient computations with noisy spiking neurons

W. Maass, Zeno Jonke, Stefan Habenschuss, 2014, ArXiv.

Pattern representation and recognition with accelerated analog neuromorphic systems

Robert A. Legenstein, Wolfgang Maass, René Schüffny, 2017, 2017 IEEE International Symposium on Circuits and Systems (ISCAS).

Oracle-Dependent Properties of the Lattice of NP Sets

Wolfgang Maass, Steven Homer, W. Maass, 1983, Theor. Comput. Sci..

Lower Bound Arguments with "Inaccessible" Numbers

Martin Dietzfelbinger, Wolfgang Maass, W. Maass, 1986, J. Comput. Syst. Sci..

Agnostic PAC Learning of Functions on Analog Neural Nets

W. Maass, 2022 .

Dimensionality and flexibility of learning in biological recurrent neural networks

Claudia Clopath, Wolfgang Maass, Rui Ponte Costa, 2020 .

Optimized spiking neurons can classify images with high accuracy through temporal coding with two spikes

Wolfgang Maass, Christoph Stöckl, W. Maass, 2020, Nature Machine Intelligence.

Simplified Rules and Theoretical Analysis for Information Bottleneck Optimization and PCA with Spiking Neurons

Wolfgang Maass, Lars Buesing, Lars Buesing, 2007, NIPS.

Autonomous Fast Learning in a Mobile Robot

Wolfgang Maass, Gerald Steinbauer, Roland Koholka, 2000, Sensor Based Intelligent Robots.

A quantitative analysis of information about past and present stimuli encoded by spikes of A1 neurons.

W. Maass, S. David, S. Shamma, 2012, Journal of neurophysiology.

On the use of inaccessible numbers and order indiscernibles in lower bound arguments for random access machines

Wolfgang Maass, W. Maass, 1988, Journal of Symbolic Logic.

On the orbits of hyperhypersimple sets

Wolfgang Maass, W. Maass, 1984, Journal of Symbolic Logic.