Mid Sweden University

miun.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
Enhancing Neural Network Generalisation with Improved Differential Evolution
Mid Sweden University, Faculty of Science, Technology and Media, Department of Computer and Electrical Engineering (2023-).ORCID iD: 0000-0001-8661-7578
Show others and affiliations
2025 (English)In: Advances in Optimization Algorithms for Multidisciplinary Engineering Applications: From Classical Methods to AI-Enhanced Solutions / [ed] Diego Oliva, Arturo Valdivia, Seyed Jalaleddin Mousavirad, Kanak Kalita, Springer, 2025, Vol. 806, p. 455-470Chapter in book (Other academic)
Abstract [en]

Training feedforward neural networks (FFNN) is a complex process that requires determining the right weights and biases, crucial parameters that largely dictate the FFNN’s effectiveness. Traditional methods like gradient descent are common in FFNN training but have limitations, including the risk of becoming trapped in local minima. Evolutionary algorithms present a solution to bypass these issues. This study takes into consideration the effectiveness of three differential evolution variations in FFNN training: the conventional DE, an opposition-based DE, and a novel centroid-based DE. The most successful among these, the centroid-based DE algorithm, called CQODTA, integrates a centroid-based method and dynamic opposition-based learning with differential evolution. The centroid method uses the centre point of the top-performing individuals as a reference for population updates, while the rest are adjusted using the usual crossover and mutation techniques. This method effectively affects the search space due to its reliance on the leading individuals. Simultaneously, the opposition-based learning concept, which takes the opposite of an existing solution, bolsters the algorithm’s ability to search broadly. We compare our trio of DE-based training methods against 14 other variants. Our thorough testing demonstrates the DE-based trainers’ adeptness at tackling various complex tasks. 

Place, publisher, year, edition, pages
Springer, 2025. Vol. 806, p. 455-470
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:miun:diva-54452DOI: 10.1007/978-3-031-78440-8_19Scopus ID: 2-s2.0-105004746720ISBN: 978-3-031-78439-2 (print)ISBN: 978-3-031-78440-8 (electronic)OAI: oai:DiVA.org:miun-54452DiVA, id: diva2:1959434
Available from: 2025-05-20 Created: 2025-05-20 Last updated: 2025-09-25Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Seyed Jalaleddin, Mousavirad

Search in DiVA

By author/editor
Seyed Jalaleddin, Mousavirad
By organisation
Department of Computer and Electrical Engineering (2023-)
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 93 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