Unsupervised learning of mid-level visual representations
Current Opinion in Neurobiology · 2024-02 · 84 · 102834
DOI: 10.1016/j.conb.2023.102834 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift Current Opinion in Neurobiology, 2024-02. Verfasst von Giulio Matteucci und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Basic Neurosciences, University of Geneva, Geneva, 1206, Switzerland. Electronic address: https://twitter.com/giulio_matt. Hauptthemen laut MEDLINE: Unsupervised Machine Learning, Machine Learning. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 111 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Ministero dell'Università e della Ricerca, Ministero dell’Istruzione, dell’Università e della Ricerca.
Abstract (Originalsprache)
Recently, a confluence between trends in neuroscience and machine learning has brought a renewed focus on unsupervised learning, where sensory processing systems learn to exploit the statistical structure of their inputs in the absence of explicit training targets or rewards. Sophisticated experimental approaches have enabled the investigation of the influence of sensory experience on neural self-organization and its synaptic bases. Meanwhile, novel algorithms for unsupervised and self-supervised learning have become increasingly popular both as inspiration for theories of the brain, particularly for the function of intermediate visual cortical areas, and as building blocks of real-world learning machines. Here we review some of these recent developments, placing them in historical context and highlighting some research lines that promise exciting breakthroughs in the near future.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Basic Neurosciences, University of Geneva, Geneva, 1206, Switzerland. Electronic address: https://twitter.com/giulio_matt.
- International School for Advanced Studies (SISSA), Trieste, 34136, Italy.
- International School for Advanced Studies (SISSA), Trieste, 34136, Italy. Electronic address: zoccolan@sissa.it.
Förderung
- Ministero dell'Università e della Ricerca
- Ministero dell’Istruzione, dell’Università e della Ricerca
Zitieren
APA
Matteucci, G., Piasini, E., & Zoccolan, D. (2024). Unsupervised learning of mid-level visual representations. Current Opinion in Neurobiology, 84, 102834. https://doi.org/10.1016/j.conb.2023.102834
Vancouver
Matteucci G, Piasini E, Zoccolan D. Unsupervised learning of mid-level visual representations. Current Opinion in Neurobiology. 2024;84:102834. doi:10.1016/j.conb.2023.102834
BibTeX
@article{Matteucci2024,
author = {Matteucci, Giulio and Piasini, Eugenio and Zoccolan, Davide},
title = {Unsupervised learning of mid-level visual representations},
journal = {Current Opinion in Neurobiology},
year = {2024},
volume = {84},
pages = {102834},
doi = {10.1016/j.conb.2023.102834}
}
EUVIMED