Preprint Open Access
Drawing Inspiration from Biological Dendrites to Empower Artificial Neural Networks
Spyridon Chavlis;
Panayiota Poirazi
Citation Style Language JSON Export
{
"publisher": "Zenodo",
"DOI": "10.5281/zenodo.4955397",
"author": [
{
"family": "Spyridon Chavlis"
},
{
"family": "Panayiota Poirazi"
}
],
"issued": {
"date-parts": [
[
2021,
6,
15
]
]
},
"abstract": "<p>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.</p>",
"title": "Drawing Inspiration from Biological Dendrites to Empower Artificial Neural Networks",
"type": "article",
"id": "4955397"
}
83
82
views
downloads
| All versions | This version | |
|---|---|---|
| Views | 83 | 83 |
| Downloads | 82 | 82 |
| Data volume | 42.6 MB | 42.6 MB |
| Unique views | 69 | 69 |
| Unique downloads | 68 | 68 |
Indexed in
- Publication date:
- June 15, 2021
- DOI:
-
- Keyword(s):
- Artificial Neural Networks Biological dendrites Plasticity
- Grants:
-
European Commission:
- NEUREKA - A smart, hybrid neural-computo device for drug discovery (863245)
- License (for files):
- Creative Commons Attribution 4.0 International