no code implementations • 22 Mar 2022 • Simone Azeglio, Simone Poetto, Luca Savant Aira, Marco Nurisso
Computational models of vision have traditionally been developed in a bottom-up fashion, by hierarchically composing a series of straightforward operations - i. e. convolution and pooling - with the aim of emulating simple and complex cells in the visual cortex, resulting in the introduction of deep convolutional neural networks (CNNs).