Toward an Integration of Deep Learning and Neuroscience

@article{Marblestone2016TowardAI,
  title={Toward an Integration of Deep Learning and Neuroscience},
  author={Adam H. Marblestone and G. Wayne and Konrad P. K{\"o}rding},
  journal={Frontiers in Computational Neuroscience},
  year={2016},
  volume={10}
}
  • Adam H. Marblestone, G. Wayne, Konrad P. Körding
  • Published 2016
  • Computer Science, Medicine, Biology
  • Frontiers in Computational Neuroscience
  • Neuroscience has focused on the detailed implementation of computation, studying neural codes, dynamics and circuits. In machine learning, however, artificial neural networks tend to eschew precisely designed codes, dynamics or circuits in favor of brute force optimization of a cost function, often using simple and relatively uniform initial architectures. Two recent developments have emerged within machine learning that create an opportunity to connect these seemingly divergent perspectives… CONTINUE READING
    Computational Principles of Supervised Learning in the Cerebellum.
    45
    Network Design and the Brain
    15
    A Biologically Plausible Learning Rule for Deep Learning in the Brain
    10
    Understanding Synthetic Gradients and Decoupled Neural Interfaces
    28
    Biologically plausible learning in a deep recurrent spiking network
    3
    Dendritic cortical microcircuits approximate the backpropagation algorithm
    61

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 738 REFERENCES
    Towards Biologically Plausible Deep Learning
    190
    Learning Through Time in the Thalamocortical Loops
    30
    A Computational Model of the Cerebral Cortex
    57
    Searching for principles of brain computation
    36
    Random feedback weights support learning in deep neural networks
    104
    Twenty-Five Lessons from Computational Neuromodulation
    98
    Supervised and Unsupervised Learning with Two Sites of Synaptic Integration
    49
    Neural Networks and Neuroscience-Inspired Computer Vision
    97
    The atoms of neural computation
    52