EUVIMEDEUVIMED entdecken
Open Access

Emergence and reconfiguration of modular structure for artificial neural networks during continual familiarity detection

Shi Gu iD, Marcelo G Mattar iD, Huajin Tang, Gang Pan iD

Science Advances · 2024

DOI: 10.1126/sciadv.adm8430 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Science Advances, 2024. Verfasst von Shi Gu und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China. Hauptthemen laut MEDLINE: Neural Networks, Computer. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 54 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Advances in artificial intelligence enable neural networks to learn a wide variety of tasks, yet our understanding of the learning dynamics of these networks remains limited. Here, we study the temporal dynamics during learning of Hebbian feedforward neural networks in tasks of continual familiarity detection. Drawing inspiration from network neuroscience, we examine the network’s dynamic reconfiguration, focusing on how network modules evolve throughout learning. Through a comprehensive assessment involving metrics like network accuracy, modular flexibility, and distribution entropy across diverse learning modes, our approach reveals various previously unknown patterns of network reconfiguration. We find that the emergence of network modularity is a salient predictor of performance and that modularization strengthens with increasing flexibility throughout learning. These insights not only elucidate the nuanced interplay of network modularity, accuracy, and learning dynamics but also bridge our understanding of learning in artificial and biological agents.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerHumansLearningArtificial IntelligenceRecognition, PsychologyAlgorithms

Autor:innen und Institutionen

  • School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China.
  • Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, China.
  • Department of Psychology, New York University, New York, NY 10003, USA.
  • College of Computer Science and Technology, Zhejiang University, Hangzhou, China.
  • State Key Laboratory of Brain Machine Intelligence, Zhejiang University, Hangzhou, China.

ORCID-Profile: Shi Gu, Marcelo G Mattar, Gang Pan

Zitieren

APA

Gu, S., Mattar, M. G., Tang, H., & Pan, G. (2024). Emergence and reconfiguration of modular structure for artificial neural networks during continual familiarity detection. Science Advances. https://doi.org/10.1126/sciadv.adm8430

Vancouver

Gu S, Mattar MG, Tang H, Pan G. Emergence and reconfiguration of modular structure for artificial neural networks during continual familiarity detection. Science Advances. 2024. doi:10.1126/sciadv.adm8430

BibTeX
@article{Gu2024,
  author = {Gu, Shi and Mattar, Marcelo G and Tang, Huajin and Pan, Gang},
  title = {Emergence and reconfiguration of modular structure for artificial neural networks during continual familiarity detection},
  journal = {Science Advances},
  year = {2024},
  doi = {10.1126/sciadv.adm8430}
}
Kostenlos starten →