paper-with-me

홈 › Papers

Single cortical neurons as deep artificial neural networks

2021-08-10 · Neuron 2021 8 · David Beniaguev, Idan Segev, Michael London

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.

📄 PDF Abstract BibTeX

Code (1)

SelfishGene/neuron_as_deep_net

Tasks

Time Series

Similar Papers 제목 키워드 기반

Towards deep learning with segregated dendrites

2016-10-01 · Jordan Guergiuev, Timothy P. Lillicrap, Blake A. Richards

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…

Deep Learning

Two-argument activation functions learn soft XOR operations like cortical neurons

2021-10-13 · KiJung Yoon, Emin Orhan, Juhyun Kim, Xaq Pitkow

Neurons in the brain are complex machines with distinct functional compartments that interact nonlinearly. In contrast, neurons in artificial neural networks abstract away this complexity, typically down to a scalar acti…

Vocal Bursts Valence Prediction

Biologically Inspired Oscillating Activation Functions Can Bridge the Performance Gap between Biological and Artificial Neurons

2021-11-07 · Matthew Mithra Noel, Shubham Bharadwaj, Venkataraman Muthiah-Nakarajan, Praneet Dutta 외

The recent discovery of special human neocortical pyramidal neurons that can individually learn the XOR function highlights the significant performance gap between biological and artificial neurons. The output of these p…

Feature Engineering

Emergent Computations in Trained Artificial Neural Networks and Real Brains

2022-12-09 · Néstor Parga, Luis Serrano-Fernández, Joan Falcó-Roget

Synaptic plasticity allows cortical circuits to learn new tasks and to adapt to changing environments. How do cortical circuits use plasticity to acquire functions such as decision-making or working memory? Neurons are c…

Decision Making

Correlation transfer by layer 5 cortical neurons under recreated synaptic inputs in vitro

2019-07-26

Correlated electrical activity in neurons is a prominent characteristic of cortical microcircuits. Despite a growing amount of evidence concerning both spike-count and subthreshold membrane potential pairwise correlation…