Single cortical neurons as deep artificial neural networks

David Beniaguev, Idan Segev, Michael London

Research output: Contribution to journalArticlepeer-review


Utilizing recent advances in machine learning, we introduce a systematic approach to characterize neurons’ input/output (I/O) mapping complexity. Deep neural networks (DNNs) were trained to faithfully replicate the I/O function of various biophysical models of cortical neurons at millisecond (spiking) resolution. A temporally convolutional DNN with five to eight layers was required to capture the I/O mapping of a realistic model of a layer 5 cortical pyramidal cell (L5PC). This DNN generalized well when presented with inputs widely outside the training distribution. When NMDA receptors were removed, a much simpler network (fully connected neural network with one hidden layer) was sufficient to fit the model. Analysis of the DNNs’ weight matrices revealed that synaptic integration in dendritic branches could be conceptualized as pattern matching from a set of spatiotemporal templates. This study provides a unified characterization of the computational complexity of single neurons and suggests that cortical networks therefore have a unique architecture, potentially supporting their computational power.

Original languageEnglish
Pages (from-to)2727-2739.e3
Issue number17
StatePublished - 1 Sep 2021


  • NMDA spike
  • calcium spike
  • compartmental model
  • cortical pyramidal neuron
  • deep learning
  • dendritic computation
  • dendritic nonlinearities
  • machine learning
  • neural coding
  • synaptic integration

All Science Journal Classification (ASJC) codes

  • Neuroscience(all)


Dive into the research topics of 'Single cortical neurons as deep artificial neural networks'. Together they form a unique fingerprint.

Cite this