When activations rival attention: novel activation functions and attention mechanisms for deep neural networks in computer vision

Alhazmi, Maan Abdulmatlub A ORCID: 0009-0002-4904-5560 (2025) When activations rival attention: novel activation functions and attention mechanisms for deep neural networks in computer vision. PhD thesis, University of Leeds.

Metadata

Supervisors: Altahhan, Abdulrahman and Bulpitt, Andy and Wang, He
Related URLs:
Keywords: Activation functions, adaptive activation functions, attention mechanisms, FER2013, ConvNeXt
Awarding institution: University of Leeds
Academic Units: The University of Leeds > Faculty of Engineering (Leeds) > School of Computing (Leeds)
Date Deposited: 19 Jun 2026 09:38
Last Modified: 19 Jun 2026 09:38
Open Archives Initiative ID (OAI ID):

Download

Final eThesis - complete (pdf)


Embargoed until: 1 July 2029

Please use the button below to request a copy.

Filename: Maan_Alhazmi_PhD_Thesis_2025.pdf

Request a copy

Export

Statistics


Please use the 'Request a copy' link(s) in the 'Downloads' section above to request this thesis. This will be sent directly to someone who may authorise access.
You can contact us about this thesis. If you need to make a general enquiry, please see the Contact us page.