Apr 20, 2026·Formal Sciences·260421.0086
Incremental learning for audio classification with Hebbian Deep Neural Networks
Riccardo Casciotti, Francesco De Santis, Alberto Antonietti, Annamaria Mesaros
This paper applies Hebbian learning principles to audio classification in a continual learning setting, introducing a kernel plasticity approach that selectively updates network weights to balance learning new sounds while retaining knowledge of previously learned ones. On the ESC-50 dataset, the method achieves 76.3% accuracy across five incremental learning steps, significantly outperforming a baseline approach.