Corpus ID: 5685993

Cortical microcircuits as gated-recurrent neural networks

@inproceedings{Costa2017CorticalMA,
  title={Cortical microcircuits as gated-recurrent neural networks},
  author={R. P. Costa and Ioannis Alexandros M. Assael and Brendan Shillingford and N. D. Freitas and T. P. Vogels},
  booktitle={NIPS},
  year={2017}
}
  • R. P. Costa, Ioannis Alexandros M. Assael, +2 authors T. P. Vogels
  • Published in NIPS 2017
  • Computer Science, Mathematics, Biology
  • Cortical circuits exhibit intricate recurrent architectures that are remarkably similar across different brain areas. Such stereotyped structure suggests the existence of common computational principles. However, such principles have remained largely elusive. Inspired by gated-memory networks, namely long short-term memory networks (LSTMs), we introduce a recurrent neural network in which information is gated through inhibitory cells that are subtractive (subLSTM). We propose a natural mapping… CONTINUE READING
    43 Citations

    Figures, Tables, and Topics from this paper

    Oscillatory recurrent gated neural integrator circuits (ORGaNICs), a unifying theoretical framework for neural dynamics
    • 8
    • PDF
    Dendritic error backpropagation in deep cortical microcircuits
    • 35
    • PDF
    Dendritic cortical microcircuits approximate the backpropagation algorithm
    • 84
    • PDF
    Modeling recurrent circuits of the primary visual cortex using neural network models
    • Highly Influenced
    • PDF
    Gating Sensory Noise in a Spiking Subtractive LSTM
    • 4
    • Highly Influenced
    • PDF
    Gated recurrent units viewed through the lens of continuous time dynamical systems
    • 12
    • PDF
    Understanding the functional and structural differences across excitatory and inhibitory neurons
    • PDF
    Long short-term memory and Learning-to-learn in networks of spiking neurons
    • 134
    • Highly Influenced
    • PDF

    References

    SHOWING 1-10 OF 88 REFERENCES
    Toward an Integration of Deep Learning and Neuroscience
    • 317
    • PDF
    Towards an integration of deep learning and neuroscience
    • 140
    Recurrent networks with short term synaptic depression
    • 52
    • PDF
    A Canonical Microcircuit for Neocortex
    • 427
    Canonical Microcircuits for Predictive Coding
    • 1,303
    • PDF
    Recurrent excitation in neocortical circuits
    • 924
    • PDF
    Efficient codes and balanced networks
    • 252
    • PDF
    Probabilistic inference of short-term synaptic plasticity in neocortical microcircuits
    • 47
    • PDF
    Inhibitory Actions Unified by Network Integration
    • 73
    Heterogeneity in the pyramidal network of the medial prefrontal cortex
    • 388
    • PDF