Neuroscience-inspired recurrent network for object recognition

Jia Ren Chang, Po Chih Kuo, Yong Sheng Chen

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

Deep neural networks inspired by the connections among biological neurons have been highly effective in the advancement of computer vision. Recent research into recurrent neural networks has taken account of forward as well as recurrent connections in a neural network architecture. In this study, we proposed a model that mirrors the architecture of the human ventral pathway with separate layers representing brain regions connected using long-range recurrent links. CIFAR-10/100 datasets were used to assess the performance of object recognition using the proposed model and the results were compared with those obtained using state-of-the-art methods. We demonstrated that the classification accuracy increased as the number of recurrences increased. Our results suggest that the proposed neuroscience-inspired model can facilitate object recognition in computer vision and may help to elucidate neurological mechanisms in the human brain.

Original languageEnglish
Title of host publication2017 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2017 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages729-734
Number of pages6
ISBN (Electronic)9781538621592
DOIs
StatePublished - 2 Jul 2017
Event25th International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2017 - Xiamen, China
Duration: 6 Nov 20179 Nov 2017

Publication series

Name2017 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2017 - Proceedings
Volume2018-January

Conference

Conference25th International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2017
CountryChina
CityXiamen
Period6/11/179/11/17

Keywords

  • neuroscience-inspired model
  • object recognition
  • ResNet

Fingerprint Dive into the research topics of 'Neuroscience-inspired recurrent network for object recognition'. Together they form a unique fingerprint.

Cite this