Biologically Inspired Semantic Lateral Connectivity for Convolutional Neural Networks

Tonio Weidler*, Julian Lehnen, Quinton Denman, Dávid Sebők, Gerhard Weiss, Kurt Driessens, Mario Senden

*Corresponding author for this work

Research output: Working paper / PreprintPreprint

Abstract

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.
Original languageEnglish
PublisherCornell University - arXiv
Publication statusPublished - 20 May 2021

Publication series

SeriesarXiv.org
Volume2105.09830

Keywords

  • computational neuroscience
  • convolutional neural networks
  • deep learning
  • lateral connectivity

Fingerprint

Dive into the research topics of 'Biologically Inspired Semantic Lateral Connectivity for Convolutional Neural Networks'. Together they form a unique fingerprint.

Cite this