Drawing Inspiration from Biological Dendrites to Empower Artificial Neural Networks
Creators
- 1. Institute of Molecular Biology and Biotechnology, Foundation for Research and Technology Hellass
- 2. Institute of Molecular Biology and Biotechnology, Foundation for Research and Technology Hellass'
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.
Files
ChavlisPoirazi2021.pdf
Files
(519.6 kB)
Name | Size | Download all |
---|---|---|
md5:0fb4219b1e2330d28e0a4828d50b199e
|
519.6 kB | Preview Download |