Evolving intelligence: Overcoming challenges for Evolutionary Deep Learning

↓ Direkt till sidans innehåll
↓ Direkt till sidans sekundära innehåll (sidomenyn)

Sökning: WFRF:(Nowaczyk Sławomir 1978 ) > Evolving intelligen...

LIBRIS Formathandbok (Information om MARC21)

Fältnamn	Indikatorer	Metadata
000		04362nam a2200469 4500
001		oai:DiVA.org:hh-52469
003		SwePub
008		240124s2024 \| \|\|\|\|\|\|\|\|\|\|\|000 \|\|eng\|
020		a 9789189587311q electronic
020		a 9789189587328q print
024	7	a https://urn.kb.se/resolve?urn=urn:nbn:se:hh:diva-524692 URI
040		a (SwePub)hh
041		a engb eng
042		9 SwePub
072	7	a vet2 swepub-contenttype
072	7	a dok2 swepub-publicationtype
100	1	a Altarabichi, Mohammed Ghaith,d 1981-u Högskolan i Halmstad,Akademin för informationsteknologi4 aut0 (Swepub:hh)mohalt
245	1 0	a Evolving intelligence :b Overcoming challenges for Evolutionary Deep Learning
264	1	a Halmstad :b Halmstad University Press,c 2024
300		a 32 s.
338		a electronic2 rdacarrier
490	0	a Halmstad University Dissertations ;v 109
520		a 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.
650	7	a TEKNIK OCH TEKNOLOGIERx Elektroteknik och elektronikx Datorsystem0 (SwePub)202062 hsv//swe
650	7	a ENGINEERING AND TECHNOLOGYx Electrical Engineering, Electronic Engineering, Information Engineeringx Computer Systems0 (SwePub)202062 hsv//eng
650	7	a TEKNIK OCH TEKNOLOGIERx Elektroteknik och elektronikx Signalbehandling0 (SwePub)202052 hsv//swe
650	7	a ENGINEERING AND TECHNOLOGYx Electrical Engineering, Electronic Engineering, Information Engineeringx Signal Processing0 (SwePub)202052 hsv//eng
653		a neural networks
653		a evolutionary deep learning
653		a evolutionary machine learning
653		a feature selection
653		a hyperparameter optimization
653		a evolutionary computation
653		a particle swarm optimization
653		a genetic algorithm
700	1	a Nowaczyk, Sławomir,c Professor,d 1978-u Högskolan i Halmstad,Akademin för informationsteknologi4 ths0 (Swepub:hh)slanow
700	1	a Pashami, Sepideh,c Associate Professor,d 1985-u Högskolan i Halmstad,Akademin för informationsteknologi4 ths0 (Swepub:hh)seppas
700	1	a Sheikholharam Mashhadi, Peyman,c Senior Lecturer,d 1982-u Högskolan i Halmstad,Akademin för informationsteknologi4 ths0 (Swepub:hh)peymas
700	1	a Lavesson, Niklas,c Professor,d 1985-u Blekinge Institute of Technology, Karlskrona, Sweden4 opn0 (Swepub:hh)seppas
710	2	a Högskolan i Halmstadb Akademin för informationsteknologi4 org
856	4	u https://hh.diva-portal.org/smash/get/diva2:1831077/FULLTEXT02.pdfx primaryx Raw objecty fulltext
856	4 8	u https://urn.kb.se/resolve?urn=urn:nbn:se:hh:diva-52469

Hitta via bibliotek

Evolving intelligence Overcoming challenges for Evolutionary Deep Learning (Sök publikationen i LIBRIS)

Till lärosätets databas

Hitta mer i SwePub

Av författaren/redakt...: Altarabichi, Moh ...; Nowaczyk, Sławom ...; Pashami, Sepideh ...; Sheikholharam Ma ...; Lavesson, Niklas ...

Om ämnet

TEKNIK OCH TEKNOLOGIER: TEKNIK OCH TEKNO ...; och Elektroteknik oc ...; och Datorsystem

TEKNIK OCH TEKNOLOGIER: TEKNIK OCH TEKNO ...; och Elektroteknik oc ...; och Signalbehandling

Delar i serien: Halmstad Univers ...

Av lärosätet: Högskolan i Halmstad

Sök utanför SwePub

Sök vidare i:: Google; Google Book Search; Google Scholar

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.

LIBRIS.kb.se