Neural networks through the lens of evolutionary dynamics

Dan C. Baciu

doi:10.1016/j.biosystems.2024.105386

Neural networks through the lens of evolutionary dynamics

Dan C. Baciu^*

^*Corresponding author for this work

History, Form & Aesthetics

Research output: Contribution to journal › Article › Scientific › peer-review

Abstract

This article revisits Artificial Neural Networks (NNs) through the lens of Evolutionary Dynamics. The two most important features of NNs are shown to reflect the two most general processes of Evolutionary Dynamics. This overlap may serve as a new and powerful connection between NNs and Evolutionary Dynamics, which encompasses a body of knowledge that has been built over multiple centuries and has been expanded to inspire applications across a vast range of disciplines. Consequently, NNs should also be applicable across the same range of disciplines—that is, much more broadly than initially envisioned. The article concludes by opening questions about NN dynamics, based on the new connection to Evolutionary Dynamics.

Original language	English
Article number	105386
Number of pages	5
Journal	BioSystems
Volume	248
DOIs	https://doi.org/10.1016/j.biosystems.2024.105386
Publication status	Published - 2025

Bibliographical note

Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care
Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Keywords

Artificial intelligence
Artificial neural networks
Evolutionary dynamics

Access to Document

10.1016/j.biosystems.2024.105386

Cite this

@article{584fc99d74de4179b187ed22e02f21b7,

title = "Neural networks through the lens of evolutionary dynamics",

abstract = "This article revisits Artificial Neural Networks (NNs) through the lens of Evolutionary Dynamics. The two most important features of NNs are shown to reflect the two most general processes of Evolutionary Dynamics. This overlap may serve as a new and powerful connection between NNs and Evolutionary Dynamics, which encompasses a body of knowledge that has been built over multiple centuries and has been expanded to inspire applications across a vast range of disciplines. Consequently, NNs should also be applicable across the same range of disciplines—that is, much more broadly than initially envisioned. The article concludes by opening questions about NN dynamics, based on the new connection to Evolutionary Dynamics.",

keywords = "Artificial intelligence, Artificial neural networks, Evolutionary dynamics",

author = "Baciu, {Dan C.}",

note = "Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.",

year = "2025",

doi = "10.1016/j.biosystems.2024.105386",

language = "English",

volume = "248",

journal = "BioSystems",

issn = "0303-2647",

publisher = "Wiley",

}

TY - JOUR

T1 - Neural networks through the lens of evolutionary dynamics

AU - Baciu, Dan C.

N1 - Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

PY - 2025

Y1 - 2025

N2 - This article revisits Artificial Neural Networks (NNs) through the lens of Evolutionary Dynamics. The two most important features of NNs are shown to reflect the two most general processes of Evolutionary Dynamics. This overlap may serve as a new and powerful connection between NNs and Evolutionary Dynamics, which encompasses a body of knowledge that has been built over multiple centuries and has been expanded to inspire applications across a vast range of disciplines. Consequently, NNs should also be applicable across the same range of disciplines—that is, much more broadly than initially envisioned. The article concludes by opening questions about NN dynamics, based on the new connection to Evolutionary Dynamics.

AB - This article revisits Artificial Neural Networks (NNs) through the lens of Evolutionary Dynamics. The two most important features of NNs are shown to reflect the two most general processes of Evolutionary Dynamics. This overlap may serve as a new and powerful connection between NNs and Evolutionary Dynamics, which encompasses a body of knowledge that has been built over multiple centuries and has been expanded to inspire applications across a vast range of disciplines. Consequently, NNs should also be applicable across the same range of disciplines—that is, much more broadly than initially envisioned. The article concludes by opening questions about NN dynamics, based on the new connection to Evolutionary Dynamics.

KW - Artificial intelligence

KW - Artificial neural networks

KW - Evolutionary dynamics

UR - http://www.scopus.com/inward/record.url?scp=85216069269&partnerID=8YFLogxK

U2 - 10.1016/j.biosystems.2024.105386

DO - 10.1016/j.biosystems.2024.105386

M3 - Article

C2 - 39753199

AN - SCOPUS:85216069269

SN - 0303-2647

VL - 248

JO - BioSystems

JF - BioSystems

M1 - 105386

ER -

Neural networks through the lens of evolutionary dynamics

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Embargoed Document

Fingerprint

Cite this