4 papers
Convolution goes higher-order: a biologically inspired mechanism empowers image classification
Simone Azeglio, Olivier Marre, Peter Neri +1
We propose a novel approach to image classification inspired by complex nonlinear biological visual processing, whereby classical convolutional neural networks (CNNs) are equipped…
Retinal processing of natural scenes : challenges ahead
Samuele Virgili, Olivier Marre
While a great deal is known about the way the retina processes simple stimuli, our understanding of how the retina processes natural stimuli is still limited. Here we highlight som…
Strong, but not weak, noise correlations are beneficial for population coding
Gabriel Mahuas, Thomas Buffet, Olivier Marre +2
Neural correlations play a critical role in sensory information coding. They are of two kinds: signal correlations, when neurons have overlapping sensitivities, and noise correlati…
Higher-Order Convolution Improves Neural Predictivity in the Retina
Simone Azeglio, Victor Calbiague Garcia, Guilhem Glaziou +3
We present a novel approach to neural response prediction that incorporates higher-order operations directly within convolutional neural networks (CNNs). Our model extends traditio…