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

@article{Maass2002RealTimeCW,
  title={Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations},
  author={W. Maass and T. Natschl{\"a}ger and H. Markram},
  journal={Neural Computation},
  year={2002},
  volume={14},
  pages={2531-2560}
}
  • W. Maass, T. Natschläger, H. Markram
  • Published 2002
  • Computer Science, Medicine
  • Neural Computation
  • A key challenge for neural modeling is to explain how a continuous stream of multimodal input from a rapidly changing environment can be processed by stereotypical recurrent circuits of integrate-and-fire neurons in real time. We propose a new computational model for real-time computing on time-varying input that provides an alternative to paradigms based on Turing machines or attractor neural networks. It does not require a task-dependent construction of neural circuits. Instead, it is based… CONTINUE READING
    Principles of real-time computing with feedback applied to cortical microcircuit models
    • 24
    • PDF
    Memory traces in dynamical systems
    • 252
    • PDF
    On the computational power of circuits of spiking neurons
    • 189
    • PDF
    Memory in linear recurrent neural networks in continuous time
    • 58
    • Highly Influenced
    • PDF
    Connectivity, Dynamics, and Memory in Reservoir Computing with Binary and Analog Neurons
    • 112
    • PDF
    Fading memory and kernel properties of generic cortical microcircuit models
    • 78
    • PDF
    Learning Universal Computations with Spikes
    • 63
    • PDF
    Spiking Neural Networks
    • 422
    • PDF

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 43 REFERENCES
    Analog Computation via Neural Networks
    • 362
    • PDF
    Neural Systems as Nonlinear Filters
    • 68
    • PDF
    What is a moment? Transient synchrony as a collective mechanism for spatiotemporal integration.
    • 284
    • Highly Influential
    • PDF
    Gradient calculations for dynamic recurrent neural networks: a survey
    • 560
    • PDF
    Temporal information transformed into a spatial code by a neural network with realistic properties
    • 415
    • PDF
    On the Computational Power of Winner-Take-All
    • 290
    • PDF
    Lower Bounds for the Computational Power of Networks of Spiking Neurons
    • W. Maass
    • Mathematics, Computer Science
    • 1996
    • 225
    • PDF