Preprint Open Access

Drawing Inspiration from Biological Dendrites to Empower Artificial Neural Networks

Spyridon Chavlis; Panayiota Poirazi

Dublin Core Export

<?xml version='1.0' encoding='utf-8'?>
<oai_dc:dc xmlns:dc="" xmlns:oai_dc="" xmlns:xsi="" xsi:schemaLocation="">
  <dc:creator>Spyridon Chavlis</dc:creator>
  <dc:creator>Panayiota Poirazi</dc:creator>
  <dc:description>This article highlights specific features of biological neurons and their dendritic trees, whose adoption may help advance artificial neural networks used in various machine learning applications. Advancements could take the form of increased computational capabilities and/or reduced power consumption. Proposed features include dendritic anatomy, dendritic nonlinearities, and compartmentalized plasticity rules, all of which shape learning and information processing in biological networks. We discuss the computational benefits provided by these features in biological neurons and suggest ways to adapt them in artificial neurons in order to exploit the respective benefits in machine learning.</dc:description>
  <dc:relation>info:eu-repo/grantAgreement/EC/Horizon 2020 Framework Programme - Research and Innovation action/863245/</dc:relation>
  <dc:subject>Artificial Neural Networks</dc:subject>
  <dc:subject>Biological dendrites</dc:subject>
  <dc:title>Drawing Inspiration from Biological Dendrites to Empower Artificial Neural Networks</dc:title>
All versions This version
Views 8383
Downloads 8282
Data volume 42.6 MB42.6 MB
Unique views 6969
Unique downloads 6868


Cite as