COMING SOON! PQDT Open is getting a new home!

ProQuest Open Access Dissertations & Theses will remain freely available as part of a new and enhanced search experience at

Questions? Please refer to this FAQ.

Dissertation/Thesis Abstract

Evolving Convolutional Neural Network Topologies for Image Recognition
by Strauch, Yaron Leander, M.S., University of Southampton (United Kingdom), 2019, 92; 28150656
Abstract (Summary)

Convolutional Neural Networks (CNNs) are state-of-the-art algorithms for image recognition. To configure a CNN properly by hand, one requires deep domain knowledge, best practises, and trial and error. As deep learning progresses, manual configuration gets harder and automated ways such as genetic algorithms are required. We describe in-depth how CNN topologies can be evolved; to do so the "half pixel problem" that occurs during programmatic CNN creation and manipulation is established, analysed and solved. A new human-readable genome representation for topologies and a novel ancestry tree visualisation for genetic algorithms is used to deepen understanding of the algorithm. We rediscover common design patterns within the topologies found and see when and how the algorithm can recover from wrong assumptions in its initialisation logic. Regularisation and partial training is introduced, allowing speed-ups of up to 19% while maintaining result accuracy.

Indexing (document details)
Advisor: Grundy, Joanna
Commitee: Charlton, Martin D.
School: University of Southampton (United Kingdom)
Department: Computer Science
School Location: England
Source: MAI 82/4(E), Masters Abstracts International
Subjects: Artificial intelligence, Computer science
Keywords: Evolutionary algorithms, Genetic algorithms, Image detection, Machine learning, Neural networks
Publication Number: 28150656
ISBN: 9798678183774
Copyright © 2021 ProQuest LLC. All rights reserved. Terms and Conditions Privacy Policy Cookie Policy