Publication
Application of Lifelong Learning with CNNs to Visual Robotic Classification Tasks
| dc.contributor.author | Zacarias, Abel | |
| dc.contributor.author | Alexandre, Luís | |
| dc.date.accessioned | 2020-01-09T11:57:55Z | |
| dc.date.available | 2020-01-09T11:57:55Z | |
| dc.date.issued | 2018-10 | |
| dc.description.abstract | The field of robotics is becoming continuously more important, due to the impact it can bring to our everyday life. A long standing problem with neural network learning is the catastrophic forgetting when one tries to use the same network to learn more than one task. In this paper we present results of the application of a method to avoid catastrophic forgetting while using Convolutional Neural Networks (CNNs) to some visual recognition tasks relevant to the field of robotics. The results show that with this method a robot can learn new tasks without forgetting the previous learned tasks. Results also showed that if we applied this method, the performance on isolated tasks increases and it is better to use it than train a CNN in an isolated way (single task). We use for our experiments two well known data sets, namely, Olivetti Faces and Fashion-MNIST. | pt_PT |
| dc.description.version | info:eu-repo/semantics/publishedVersion | pt_PT |
| dc.identifier.uri | http://hdl.handle.net/10400.6/8157 | |
| dc.language.iso | eng | pt_PT |
| dc.peerreviewed | yes | pt_PT |
| dc.title | Application of Lifelong Learning with CNNs to Visual Robotic Classification Tasks | pt_PT |
| dc.type | conference object | |
| dspace.entity.type | Publication | |
| oaire.citation.title | 24th Portuguese Conference on Pattern Recognition, RECPAD 2018 | pt_PT |
| person.familyName | Zacarias | |
| person.familyName | Alexandre | |
| person.givenName | Abel | |
| person.givenName | Luís | |
| person.identifier.ciencia-id | 7612-6C59-2F02 | |
| person.identifier.ciencia-id | 2014-0F06-A3E3 | |
| person.identifier.orcid | 0000-0002-0226-9682 | |
| person.identifier.orcid | 0000-0002-5133-5025 | |
| person.identifier.rid | E-8770-2013 | |
| person.identifier.scopus-author-id | 8847713100 | |
| rcaap.rights | openAccess | pt_PT |
| rcaap.type | conferenceObject | pt_PT |
| relation.isAuthorOfPublication | 9f46b558-e59e-4c92-95ac-7f3f06b0ed16 | |
| relation.isAuthorOfPublication | 131ec6eb-b61a-4f27-953f-12e948a43a96 | |
| relation.isAuthorOfPublication.latestForDiscovery | 131ec6eb-b61a-4f27-953f-12e948a43a96 |