Training Convolutional Neural Networks with Competitive Hebbian Learning Approaches
- 1. University of Pisa
- 2. CNR-ISTI
Description
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.
Notes
Files
ACAIN2021_paper_20.pdf
Files
(519.7 kB)
Name | Size | Download all |
---|---|---|
md5:0e518291c88a6e2eb41f885e3885ba3b
|
519.7 kB | Preview Download |