https://www.sciencedirect.com/science/article/pii/S0896627321005018?dgcid=coauthor JavaScript is disabled on your browser. Please enable JavaScript to use all the features on this page. [1628809277] Skip to main content Skip to article Elsevier logo * Journals & Books * * RegisterSign in Sign inRegister * Journals & Books * Help View PDF * Seamless access Access through your institution * Purchase PDF [ ] Neuron Neuron Available online 10 August 2021 In Press, Corrected ProofWhat are Corrected Proof articles? Journal home page for Neuron Article Single cortical neurons as deep artificial neural networks Author links open overlay panelDavidBeniaguev^1^3IdanSegev^1^2Michael London^1^2 Show more Share Cite https://doi.org/10.1016/j.neuron.2021.07.002Get rights and content Highlights * Cortical neurons are well approximated by a deep neural network (DNN) with 5-8 layers * DNN's depth arises from the interaction between NMDA receptors and dendritic morphology * Dendritic branches can be conceptualized as a set of spatiotemporal pattern detectors * We provide a unified method to assess the computational complexity of any neuron type Summary 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. Graphical abstract [1-s2] 1. Download : Download high-res image (228KB) 2. Download : Download full-size image Keywords deep learning machine learning synaptic integration cortical pyramidal neuron compartmental model dendritic nonlinearities dendritic computation neural coding NMDA spike calcium spike Recommended articlesCiting articles (0) Data and code availability All data and pre-trained networks that were used in this work are available on Kaggle datasets platform (https://doi.org/10.34740/ kaggle/ds/417817) at the following link: https://www.kaggle.com/selfishgene/ single-neurons-as-deep-nets-nmda-test-data Additionally, the dataset was deposited to Mendeley Data (https:// doi.org/10.17632/xjvsp3dhzf.2) at the link: https://data.mendeley.com/datasets/xjvsp3dhzf/2 A github repository of all simulation, fitting and evaluation code can be found in the following link: https://github.com/SelfishGene/neuron_as_deep_net. Additionally, we provide a python script that loads a pretrained artificial network and makes a prediction on the entire NMDA test set that replicates the main result of the paper (Figure 2): https://www.kaggle.com/selfishgene/ single-neuron-as-deep-net-replicating-key-result. Also, a python script that loads the data and explores the dataset ( Figure S1) can be found in the following link: https://www.kaggle.com /selfishgene/exploring-a-single-cortical-neuron. ^3 Lead contact View full text (c) 2021 Elsevier Inc. Recommended articles No articles found. Citing articles Article Metrics View article metrics Elsevier logo * About ScienceDirect * Remote access * Shopping cart * Advertise * Contact and support * Terms and conditions * Privacy policy We use cookies to help provide and enhance our service and tailor content and ads. By continuing you agree to the use of cookies. Copyright (c) 2021 Elsevier B.V. or its licensors or contributors. ScienceDirect (r) is a registered trademark of Elsevier B.V. ScienceDirect (r) is a registered trademark of Elsevier B.V. RELX group home page