kth.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Adaptive Learning without Forgetting via Low-Complexity Convex Networks
KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Information Science and Engineering.ORCID iD: 0000-0002-8534-7622
KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Information Science and Engineering.ORCID iD: 0000-0003-4406-536x
KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Information Science and Engineering.ORCID iD: 0000-0002-7926-5081
KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Information Science and Engineering.ORCID iD: 0000-0003-2638-6047
2020 (English)In: 28th European Signal Processing Conference (EUSIPCO 2020), Institute of Electrical and Electronics Engineers (IEEE) , 2020, p. 1623-1627Conference paper, Published paper (Refereed)
Abstract [en]

We study the problem of learning without forgetting (LwF) in which a deep learning model learns new tasks without a significant drop in the classification performance on the previously learned tasks. We propose an LwF algorithm for multilayer feedforward neural networks in which we can adapt the number of layers of the network from the old task to the new task. To this end, we limit ourselves to convex loss functions in order to train the network in a layer-wise manner. Layer-wise convex optimization leads to low-computational complexity and provides a more interpretable understanding of the network. We compare the effectiveness of the proposed adaptive LwF algorithm with the standard LwF over image classification datasets.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE) , 2020. p. 1623-1627
Series
European Signal Processing Conference, ISSN 2076-1465
Keywords [en]
learning without forgetting, convex neural networks, size adaptive, low complexity
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:kth:diva-295259DOI: 10.23919/Eusipco47968.2020.9287632ISI: 000632622300327Scopus ID: 2-s2.0-85099319352OAI: oai:DiVA.org:kth-295259DiVA, id: diva2:1560138
Conference
28th European Signal Processing Conference (EUSIPCO), JAN 18-22, 2021, ELECTR NETWORK
Note

QC 20210621

Available from: 2021-06-03 Created: 2021-06-03 Last updated: 2023-04-05Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Javid, Alireza M.Liang, XinyueSkoglund, MikaelChatterjee, Saikat

Search in DiVA

By author/editor
Javid, Alireza M.Liang, XinyueSkoglund, MikaelChatterjee, Saikat
By organisation
Information Science and Engineering
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 18 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf