2 papers
q-bio.NC2021
Emergence of Lie symmetries in functional architectures learned by CNNs
Federico Bertoni, Noemi Montobbio, Alessandro Sarti +1
In this paper we study the spontaneous development of symmetries in the early layers of a Convolutional Neural Network (CNN) during learning on natural images. Our architecture is…
cs.NE2019
LGN-CNN: a biologically inspired CNN architecture
Federico Bertoni, Giovanna Citti, Alessandro Sarti
In this paper we introduce a biologically inspired Convolutional Neural Network (CNN) architecture called LGN-CNN that has a first convolutional layer composed by a single filter t…