No Cover Image

Journal article 549 views

Deep Learning Neural Networks as a Model of Saccadic Generation

Sofia Krasovskaya, Georgiy Zhulikov, Joe MacInnes Orcid Logo

SSRN Electronic Journal

Swansea University Author: Joe MacInnes Orcid Logo

Full text not available from this repository: check for access using links below.

Check full text

DOI (Published version): 10.2139/ssrn.3262650

Abstract

Approximately twenty years ago, Laurent Itti and Christof Koch created a model of saliency in visual attention in an attempt to recreate the work of biological pyramidal neurons by mimicking neurons with centre-surround receptive fields. The Saliency Model has launched many studies that contributed...

Full description

Published in: SSRN Electronic Journal
ISSN: 1556-5068
Published: Elsevier BV
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa63401
first_indexed 2023-05-31T08:23:26Z
last_indexed 2024-11-15T18:01:31Z
id cronfa63401
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2023-06-08T15:05:23.8171709</datestamp><bib-version>v2</bib-version><id>63401</id><entry>2023-05-11</entry><title>Deep Learning Neural Networks as a Model of Saccadic Generation</title><swanseaauthors><author><sid>06dcb003ec50192bafde2c77bef4fd5c</sid><ORCID>0000-0002-5134-1601</ORCID><firstname>Joe</firstname><surname>MacInnes</surname><name>Joe MacInnes</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2023-05-11</date><deptcode>MACS</deptcode><abstract>Approximately twenty years ago, Laurent Itti and Christof Koch created a model of saliency in visual attention in an attempt to recreate the work of biological pyramidal neurons by mimicking neurons with centre-surround receptive fields. The Saliency Model has launched many studies that contributed to the understanding of layers of vision and the sphere of visual attention. The aim of the current study is to improve this model by using an artificial neural network as the spatial component of a model that generates saccades similar to how humans make saccadic eye movements. The proposed model uses a Leaky Integrate-and-Fire layer for temporal predictions, and replaces parallel feature maps with a deep learning neural network in order to create a generative model that is precise for both spatial and temporal shifts of attention. Our model was able to predict eye movements based on unsupervised learning from raw image input, combined with supervised learning from fixation maps retrieved during an eye-tracking experiment. The results imply that it is possible to match the spatial and temporal distributions of the model to spatial and temporal human distributions.</abstract><type>Journal Article</type><journal>SSRN Electronic Journal</journal><volume/><journalNumber/><paginationStart/><paginationEnd/><publisher>Elsevier BV</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic>1556-5068</issnElectronic><keywords/><publishedDay>0</publishedDay><publishedMonth>0</publishedMonth><publishedYear>0</publishedYear><publishedDate>0001-01-01</publishedDate><doi>10.2139/ssrn.3262650</doi><url>http://dx.doi.org/10.2139/ssrn.3262650</url><notes/><college>COLLEGE NANME</college><department>Mathematics and Computer Science School</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>MACS</DepartmentCode><institution>Swansea University</institution><apcterm/><funders/><projectreference/><lastEdited>2023-06-08T15:05:23.8171709</lastEdited><Created>2023-05-11T11:27:58.9186481</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>Sofia</firstname><surname>Krasovskaya</surname><order>1</order></author><author><firstname>Georgiy</firstname><surname>Zhulikov</surname><order>2</order></author><author><firstname>Joe</firstname><surname>MacInnes</surname><orcid>0000-0002-5134-1601</orcid><order>3</order></author></authors><documents/><OutputDurs/></rfc1807>
spelling 2023-06-08T15:05:23.8171709 v2 63401 2023-05-11 Deep Learning Neural Networks as a Model of Saccadic Generation 06dcb003ec50192bafde2c77bef4fd5c 0000-0002-5134-1601 Joe MacInnes Joe MacInnes true false 2023-05-11 MACS Approximately twenty years ago, Laurent Itti and Christof Koch created a model of saliency in visual attention in an attempt to recreate the work of biological pyramidal neurons by mimicking neurons with centre-surround receptive fields. The Saliency Model has launched many studies that contributed to the understanding of layers of vision and the sphere of visual attention. The aim of the current study is to improve this model by using an artificial neural network as the spatial component of a model that generates saccades similar to how humans make saccadic eye movements. The proposed model uses a Leaky Integrate-and-Fire layer for temporal predictions, and replaces parallel feature maps with a deep learning neural network in order to create a generative model that is precise for both spatial and temporal shifts of attention. Our model was able to predict eye movements based on unsupervised learning from raw image input, combined with supervised learning from fixation maps retrieved during an eye-tracking experiment. The results imply that it is possible to match the spatial and temporal distributions of the model to spatial and temporal human distributions. Journal Article SSRN Electronic Journal Elsevier BV 1556-5068 0 0 0 0001-01-01 10.2139/ssrn.3262650 http://dx.doi.org/10.2139/ssrn.3262650 COLLEGE NANME Mathematics and Computer Science School COLLEGE CODE MACS Swansea University 2023-06-08T15:05:23.8171709 2023-05-11T11:27:58.9186481 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Sofia Krasovskaya 1 Georgiy Zhulikov 2 Joe MacInnes 0000-0002-5134-1601 3
title Deep Learning Neural Networks as a Model of Saccadic Generation
spellingShingle Deep Learning Neural Networks as a Model of Saccadic Generation
Joe MacInnes
title_short Deep Learning Neural Networks as a Model of Saccadic Generation
title_full Deep Learning Neural Networks as a Model of Saccadic Generation
title_fullStr Deep Learning Neural Networks as a Model of Saccadic Generation
title_full_unstemmed Deep Learning Neural Networks as a Model of Saccadic Generation
title_sort Deep Learning Neural Networks as a Model of Saccadic Generation
author_id_str_mv 06dcb003ec50192bafde2c77bef4fd5c
author_id_fullname_str_mv 06dcb003ec50192bafde2c77bef4fd5c_***_Joe MacInnes
author Joe MacInnes
author2 Sofia Krasovskaya
Georgiy Zhulikov
Joe MacInnes
format Journal article
container_title SSRN Electronic Journal
institution Swansea University
issn 1556-5068
doi_str_mv 10.2139/ssrn.3262650
publisher Elsevier BV
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
url http://dx.doi.org/10.2139/ssrn.3262650
document_store_str 0
active_str 0
description Approximately twenty years ago, Laurent Itti and Christof Koch created a model of saliency in visual attention in an attempt to recreate the work of biological pyramidal neurons by mimicking neurons with centre-surround receptive fields. The Saliency Model has launched many studies that contributed to the understanding of layers of vision and the sphere of visual attention. The aim of the current study is to improve this model by using an artificial neural network as the spatial component of a model that generates saccades similar to how humans make saccadic eye movements. The proposed model uses a Leaky Integrate-and-Fire layer for temporal predictions, and replaces parallel feature maps with a deep learning neural network in order to create a generative model that is precise for both spatial and temporal shifts of attention. Our model was able to predict eye movements based on unsupervised learning from raw image input, combined with supervised learning from fixation maps retrieved during an eye-tracking experiment. The results imply that it is possible to match the spatial and temporal distributions of the model to spatial and temporal human distributions.
published_date 0001-01-01T02:41:30Z
_version_ 1822005752260198400
score 11.048042

Similar Items