English

Towards deep learning with segregated dendrites

Neurons and Cognition 2017-04-11 v3

Abstract

Deep learning has led to significant advances in artificial intelligence, in part, by adopting strategies motivated by neurophysiology. However, it is unclear whether deep learning could occur in the real brain. Here, we show that a deep learning algorithm that utilizes multi-compartment neurons might help us to understand how the brain optimizes cost functions. Like neocortical pyramidal neurons, neurons in our model receive sensory information and higher-order feedback in electrotonically segregated compartments. Thanks to this segregation, the neurons in different layers of the network can coordinate synaptic weight updates. As a result, the network can learn to categorize images better than a single layer network. Furthermore, we show that our algorithm takes advantage of multilayer architectures to identify useful representations---the hallmark of deep learning. This work demonstrates that deep learning can be achieved using segregated dendritic compartments, which may help to explain the dendritic morphology of neocortical pyramidal neurons.

Keywords

Cite

@article{arxiv.1610.00161,
  title  = {Towards deep learning with segregated dendrites},
  author = {Jordan Guergiuev and Timothy P. Lillicrap and Blake A. Richards},
  journal= {arXiv preprint arXiv:1610.00161},
  year   = {2017}
}

Comments

41 pages, 11 figures

R2 v1 2026-06-22T16:07:39.283Z