Evaluation of the Hierarchical Correspondence between the Human Brain and Artificial Neural Networks: A Review
Biology · 12.10.2023 · 12 (10) · 1330
DOI: 10.3390/biology12101330 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift Biology, online erschienen am 12.10.2023. Verfasst von Trung Quang Pham und 2 weiteren Autor:innen. Beteiligte Einrichtung: Araya Inc., Tokyo 101-0025, Japan. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 96 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: JSPS KAKENHI, Core Research for Evolutionary Science and Technology (CREST), Japan Agency for Medical Research and Development (AMED).
Abstract (Originalsprache)
Artificial neural networks (ANNs) that are heavily inspired by the human brain now achieve human-level performance across multiple task domains. ANNs have thus drawn attention in neuroscience, raising the possibility of providing a framework for understanding the information encoded in the human brain. However, the correspondence between ANNs and the brain cannot be measured directly. They differ in outputs and substrates, neurons vastly outnumber their ANN analogs (i.e., nodes), and the key algorithm responsible for most of modern ANN training (i.e., backpropagation) is likely absent from the brain. Neuroscientists have thus taken a variety of approaches to examine the similarity between the brain and ANNs at multiple levels of their information hierarchy. This review provides an overview of the currently available approaches and their limitations for evaluating brain–ANN correspondence.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Araya Inc., Tokyo 101-0025, Japan.
- Graduate School of Brain Science, Doshisha University, Kyoto 610-0321, Japan.
ORCID-Profile: Junichi Chikazoe
Förderung
- JSPS KAKENHI
- Core Research for Evolutionary Science and Technology (CREST)
- Japan Agency for Medical Research and Development (AMED)
Zitieren
APA
Pham, T. Q., Matsui, T., & Chikazoe, J. (2023). Evaluation of the Hierarchical Correspondence between the Human Brain and Artificial Neural Networks: A Review. Biology, 12(10), 1330. https://doi.org/10.3390/biology12101330
Vancouver
Pham TQ, Matsui T, Chikazoe J. Evaluation of the Hierarchical Correspondence between the Human Brain and Artificial Neural Networks: A Review. Biology. 2023;12(10):1330. doi:10.3390/biology12101330
BibTeX
@article{Pham2023,
author = {Pham, Trung Quang and Matsui, Teppei and Chikazoe, Junichi},
title = {Evaluation of the Hierarchical Correspondence between the Human Brain and Artificial Neural Networks: A Review},
journal = {Biology},
year = {2023},
volume = {12},
number = {10},
pages = {1330},
doi = {10.3390/biology12101330}
}
EUVIMED