Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations
From MaRDI portal
Publication:4409375
DOI10.1162/089976602760407955zbMath1057.68618WikidataQ28214969 ScholiaQ28214969MaRDI QIDQ4409375
Wolfgang Maass, Henry Markram, Thomas Nathschläger
Publication date: 2002
Published in: Neural Computation (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1162/089976602760407955
68Q10: Modes of computation (nondeterministic, parallel, interactive, probabilistic, etc.)
Related Items
Local Interactions in Neural Networks Explain Global Effects in Gestalt Processing and Masking, Real-Time Computation at the Edge of Chaos in Recurrent Neural Networks, The criticality hypothesis: how local cortical networks might optimize information processing, Phase Precession Through Synaptic Facilitation, Learning Beyond Finite Memory in Recurrent Networks of Spiking Neurons, Polychronization: Computation with Spikes, Movement Generation with Circuits of Spiking Neurons, Identification of pre-sliding friction dynamics, Analysis and Design of Echo State Networks, Computational theories on the function of theta oscillations, On the computational power of circuits of spiking neurons, The cerebellum as a liquid state machine, From memory-based decisions to decision-based movements: A model of interval discrimination followed by action selection, Fading memory and time series prediction in recurrent networks with different forms of plasticity, Edge of chaos and prediction of computational performance for neural circuit models, Optimization and applications of echo state networks with leaky- integrator neurons, Online reservoir adaptation by intrinsic plasticity for backpropagation-decorrelation and echo state learning, Decoupled echo state networks with lateral inhibition, An associative memory readout for ESNs with applications to dynamical pattern recognition, An experimental unification of reservoir computing methods, Learning grammatical structure with Echo State Networks, Modelling memory functions with recurrent neural networks consisting of input compensation units: I. Static situations, Travelling wave patterns in a model of the spinal pattern generator using spiking neurons, A model for the interaction of oscillations and pattern generation with real-time computing in generic neural microcircuit models, Decoding a Temporal Population Code, A Reproducing Kernel Hilbert Space Framework for Spike Train Signal Processing, Chemosensor-Driven Artificial Antennal Lobe Transient Dynamics Enable Fast Recognition and Working Memory, Recurrent Infomax Generates Cell Assemblies, Neuronal Avalanches, and Simple Cell-Like Selectivity, FREEMAN'S K MODELS AS RESERVOIR COMPUTING ARCHITECTURES
Cites Work
