ExGate: Externally Controlled Gating for Feature-based Attention in Artificial Neural Networks

Jarryd Son, Amit Kumar Mishra

Research output: Chapter in Book/Report/Conference proceedingConference Proceeding (Non-Journal item)

Abstract

The perceptual capabilities of artificial systems have come a long way since the advent of deep learning. These methods have proven to be effective, however, they are not as efficient as their biological counterparts. Visual attention is a set of mechanisms that are employed in biological visual systems to ease the computational load by only processing pertinent parts of the stimuli. This paper addresses the implementation of top-down, feature-based attention in an artificial neural network by the use of externally controlled neuron gating. Our results showed a 5% increase in classification accuracy on the CIFAR-10 dataset versus a non-gated version while adding a limited number of parameters. Our gated model also produces more reasonable errors in predictions by drastically reducing the prediction of classes that belong to a different category than the true class.

Original languageEnglish
Title of host publication2022 International Joint Conference on Neural Networks, IJCNN 2022 - Proceedings
PublisherIEEE Press
Number of pages7
ISBN (Electronic)9781728186719
DOIs
Publication statusPublished - 30 Sept 2022
Externally publishedYes
Event2022 International Joint Conference on Neural Networks, IJCNN 2022 - Padua, Italy
Duration: 18 Jul 202223 Jul 2022

Publication series

NameProceedings of the International Joint Conference on Neural Networks
Volume2022-July

Conference

Conference2022 International Joint Conference on Neural Networks, IJCNN 2022
Country/TerritoryItaly
CityPadua
Period18 Jul 202223 Jul 2022

Keywords

  • attention
  • neural networks
  • perception

Fingerprint

Dive into the research topics of 'ExGate: Externally Controlled Gating for Feature-based Attention in Artificial Neural Networks'. Together they form a unique fingerprint.

Cite this