Biologically Inspired Semantic Lateral Connectivity for Convolutional Neural Networks

Lateral connections play an important role for sensory processing in visual cortex by supporting discriminable neuronal responses even to highly similar features. In the present work, we show that establishing a biologically inspired Mexican hat lateral connectivity profile along the filter domain c...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Weidler, Tonio, Lehnen, Julian, Denman, Quinton, Sebők, Dávid, Weiss, Gerhard, Driessens, Kurt, Senden, Mario
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 20.05.2021
Subjects
Artificial neural networks
Connectivity
Neural networks
Selectivity
Online AccessGet full text

Cover

More Information
Summary:Lateral connections play an important role for sensory processing in visual cortex by supporting discriminable neuronal responses even to highly similar features. In the present work, we show that establishing a biologically inspired Mexican hat lateral connectivity profile along the filter domain can significantly improve the classification accuracy of a variety of lightweight convolutional neural networks without the addition of trainable network parameters. Moreover, we demonstrate that it is possible to analytically determine the stationary distribution of modulated filter activations and thereby avoid using recurrence for modeling temporal dynamics. We furthermore reveal that the Mexican hat connectivity profile has the effect of ordering filters in a sequence resembling the topographic organization of feature selectivity in early visual cortex. In an ordered filter sequence, this profile then sharpens the filters' tuning curves.
ISSN:2331-8422