EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Delving into Unsupervised Hebbian Learning from Artificial Intelligence Perspectives

Wei Lin, Zhixin Piao, Chi Chung Alan Fung

Machine Learning and Knowledge Extraction · 11.11.2025 · 7 (4) · 143

DOI: 10.3390/make7040143 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Machine Learning and Knowledge Extraction, online erschienen am 11.11.2025. Verfasst von Wei Lin und 2 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: City University of Hong Kong, Science, Technology and Innovation Commission of Shenzhen Municipality.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Unsupervised Hebbian learning is a biologically inspired algorithm designed to extract representations from input images, which can subsequently support supervised learning. It presents a promising alternative to traditional artificial neural networks (ANNs). Many attempts have focused on enhancing Hebbian learning by incorporating more biologically plausible components. Contrarily, we draw inspiration from recent advances in ANNs to rethink and further improve Hebbian learning in three interconnected aspects. First, we investigate the issue of overfitting in Hebbian learning and emphasize the importance of selecting an optimal number of training epochs, even in unsupervised settings. In addition, we discuss the risks and benefits of anti-Hebbian learning in model performance, and our visualizations reveal that synapses resembling the input images sometimes do not necessarily reflect effective learning. Then, we explore the impact of different activation functions on Hebbian representations, highlighting the benefits of properly utilizing negative values. Furthermore, motivated by the success of large pre-trained language models, we propose a novel approach for leveraging unlabeled data from other datasets. Unlike conventional pre-training in ANNs, experimental results demonstrate that merging trained synapses from different datasets leads to improved performance. Overall, our findings offer fresh perspectives on enhancing the future design of Hebbian learning algorithms.

Förderung

  • City University of Hong Kong
  • Science, Technology and Innovation Commission of Shenzhen Municipality

Zitieren

APA

Lin, W., Piao, Z., & Fung, C. C. A. (2025). Delving into Unsupervised Hebbian Learning from Artificial Intelligence Perspectives. Machine Learning and Knowledge Extraction, 7(4), 143. https://doi.org/10.3390/make7040143

Vancouver

Lin W, Piao Z, Fung CCA. Delving into Unsupervised Hebbian Learning from Artificial Intelligence Perspectives. Machine Learning and Knowledge Extraction. 2025;7(4):143. doi:10.3390/make7040143

BibTeX
@article{Lin2025,
  author = {Lin, Wei and Piao, Zhixin and Fung, Chi Chung Alan},
  title = {Delving into Unsupervised Hebbian Learning from Artificial Intelligence Perspectives},
  journal = {Machine Learning and Knowledge Extraction},
  year = {2025},
  volume = {7},
  number = {4},
  pages = {143},
  doi = {10.3390/make7040143}
}
Kostenlos starten →