Published February 2, 2022 | Version v1
Conference paper Open

Training Convolutional Neural Networks with Competitive Hebbian Learning Approaches

  • 1. University of Pisa
  • 2. CNR-ISTI


We explore competitive Hebbian learning strategies to train feature detectors in Convolutional Neural Networks (CNNs), without supervision. We consider variants of the Winner-Takes-All (WTA) strategy explored in previous works, i.e. k-WTA, e-soft-WTA and p-soft-WTA, performing experiments on different object recognition datasets. Results suggest that the Hebbian approaches are effective to train early feature extraction layers, or to re-train higher layers of a pre-trained network, with soft competition generally performing better than other Hebbian approaches explored in this work. Our findings encourage a path of cooperation between neuroscience and computer science towards a deeper investigation of biologically inspired learning principles.


In Nicosia G. et al. (eds) Machine Learning, Optimization, and Data Science. LOD 2021. Lecture Notes in Computer Science, vol 13163. Springer, Cham.



Files (519.7 kB)

Name Size Download all
519.7 kB Preview Download

Additional details


AI4Media – A European Excellence Centre for Media, Society and Democracy 951911
European Commission
AI4EU – A European AI On Demand Platform and Ecosystem 825619
European Commission