Dendrites endow artificial neural networks with accurate, robust and parameter-efficient learning

Chavlis, Spyridon; Poirazi, Panayiota

doi:10.1038/s41467-025-56297-9

articleNature CommunicationsJan 22, 2025GOLD OA

Dendrites endow artificial neural networks with accurate, robust and parameter-efficient learning

SCSpyridon Chavlis PPPanayiota Poirazi

Foundation for Research and Technology Hellas · Institute of Molecular Biology and Biotechnology

PubMed

Indexed inarxivcrossrefdatacitedoajpubmed

Abstract

Artificial neural networks (ANNs) are at the core of most Deep Learning (DL) algorithms that successfully tackle complex problems like image recognition, autonomous driving, and natural language processing. However, unlike biological brains who tackle similar problems in a very efficient manner, DL algorithms require a large number of trainable parameters, making them energy-intensive and prone to overfitting. Here, we show that a new ANN architecture that incorporates the structured connectivity and restricted sampling properties of biological dendrites counteracts these limitations. We find that dendritic ANNs are more robust to overfitting and match or outperform traditional ANNs on several image…

Citation impact

48

total citations

FWCI: 27.40
Percentile: 100%
References: 116

Citations per year

Authors

2

Topics & keywords

Topics

Keywords

Overfitting
Computer science
Artificial intelligence
Artificial neural network
Machine learning
Class (philosophy)
Deep learning

UN Sustainable Development Goals

Quality Education

No related works found for this paper.