Search: onr:"swepub:oai:DiVA.org:hh-52469" >
Evolving intelligen...
-
Altarabichi, Mohammed Ghaith,1981-Högskolan i Halmstad,Akademin för informationsteknologi
(author)
Evolving intelligence : Overcoming challenges for Evolutionary Deep Learning
Publisher, publication year, extent ...
-
Halmstad :Halmstad University Press,2024
-
32 s.
-
electronicrdacarrier
Numbers
-
LIBRIS-ID:oai:DiVA.org:hh-52469
-
ISBN:9789189587311
-
ISBN:9789189587328
-
https://urn.kb.se/resolve?urn=urn:nbn:se:hh:diva-52469URI
Supplementary language notes
-
Language:English
-
Summary in:English
Part of subdatabase
Classification
-
Subject category:vet swepub-contenttype
-
Subject category:dok swepub-publicationtype
Series
-
Halmstad University Dissertations ;109
Notes
-
Deep Learning (DL) has achieved remarkable results in both academic and industrial fields over the last few years. However, DL models are often hard to design and require proper selection of features and tuning of hyper-parameters to achieve high performance. These selections are tedious for human experts and require substantial time and resources. A difficulty that encouraged a growing number of researchers to use Evolutionary Computation (EC) algorithms to optimize Deep Neural Networks (DNN); a research branch called Evolutionary Deep Learning (EDL).This thesis is a two-fold exploration within the domains of EDL, and more broadly Evolutionary Machine Learning (EML). The first goal is to makeEDL/EML algorithms more practical by reducing the high computational costassociated with EC methods. In particular, we have proposed methods to alleviate the computation burden using approximate models. We show that surrogate-models can speed up EC methods by three times without compromising the quality of the final solutions. Our surrogate-assisted approach allows EC methods to scale better for both, expensive learning algorithms and large datasets with over 100K instances. Our second objective is to leverage EC methods for advancing our understanding of Deep Neural Network (DNN) design. We identify a knowledge gap in DL algorithms and introduce an EC algorithm precisely designed to optimize this uncharted aspect of DL design. Our analytical focus revolves around revealing avant-garde concepts and acquiring novel insights. In our study of randomness techniques in DNN, we offer insights into the design and training of more robust and generalizable neural networks. We also propose, in another study, a novel survival regression loss function discovered based on evolutionary search.
Subject headings and genre
Added entries (persons, corporate bodies, meetings, titles ...)
-
Nowaczyk, Sławomir,Professor,1978-Högskolan i Halmstad,Akademin för informationsteknologi(Swepub:hh)slanow
(thesis advisor)
-
Pashami, Sepideh,Associate Professor,1985-Högskolan i Halmstad,Akademin för informationsteknologi(Swepub:hh)seppas
(thesis advisor)
-
Sheikholharam Mashhadi, Peyman,Senior Lecturer,1982-Högskolan i Halmstad,Akademin för informationsteknologi(Swepub:hh)peymas
(thesis advisor)
-
Lavesson, Niklas,Professor,1985-Blekinge Institute of Technology, Karlskrona, Sweden(Swepub:hh)seppas
(opponent)
-
Högskolan i HalmstadAkademin för informationsteknologi
(creator_code:org_t)
Internet link
Find in a library
To the university's database