Emergence of Lie symmetries in functional architectures learned by CNNs

by   Federico Bertoni, et al.

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 built in such a way to mimic the early stages of biological visual systems. In particular, it contains a pre-filtering step ℓ^0 defined in analogy with the Lateral Geniculate Nucleus (LGN). Moreover, the first convolutional layer is equipped with lateral connections defined as a propagation driven by a learned connectivity kernel, in analogy with the horizontal connectivity of the primary visual cortex (V1). The layer ℓ^0 shows a rotational symmetric pattern well approximated by a Laplacian of Gaussian (LoG), which is a well-known model of the receptive profiles of LGN cells. The convolutional filters in the first layer can be approximated by Gabor functions, in agreement with well-established models for the profiles of simple cells in V1. We study the learned lateral connectivity kernel of this layer, showing the emergence of orientation selectivity w.r.t. the learned filters. We also examine the association fields induced by the learned kernel, and show qualitative and quantitative comparisons with known group-based models of V1 horizontal connectivity. These geometric properties arise spontaneously during the training of the CNN architecture, analogously to the emergence of symmetries in visual systems thanks to brain plasticity driven by external stimuli.


page 1

page 8

page 9

page 10

page 12


LGN-CNN: a biologically inspired CNN architecture

In this paper we introduce a biologically inspired CNN architecture that...

Revealing Fine Structures of the Retinal Receptive Field by Deep Learning Networks

Deep convolutional neural networks (CNNs) have demonstrated impressive p...

KerCNNs: biologically inspired lateral connections for classification of corrupted images

The state of the art in many computer vision tasks is represented by Con...

Learning a smooth kernel regularizer for convolutional neural networks

Modern deep neural networks require a tremendous amount of data to train...

How Convolutional Neural Network Architecture Biases Learned Opponency and Colour Tuning

Recent work suggests that changing Convolutional Neural Network (CNN) ar...

A sub-Riemannian model of the visual cortex with frequency and phase

In this paper we present a novel model of the primary visual cortex (V1)...

Local and global gestalt laws: A neurally based spectral approach

A mathematical model of figure-ground articulation is presented, taking ...