國立高雄大學圖資館 |

Language: English

Back

Evolutionary multi-task optimizationfoundations and methodologies /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Evolutionary multi-task optimizationby Liang Feng ... [et al.].
Reminder of title:	foundations and methodologies /
other author:	Feng, Liang.
Published:	Singapore :Springer Nature Singapore :2023.
Description:	x, 219 p. :ill., digital ;24 cm.
Contained By:	Springer Nature eBook
Subject:	Evolutionary computation.
Online resource:	https://doi.org/10.1007/978-981-19-5650-8
ISBN:	9789811956508$q(electronic bk.)

Evolutionary multi-task optimizationfoundations and methodologies /
Evolutionary multi-task optimizationfoundations and methodologies /[electronic resource] :by Liang Feng ... [et al.]. - Singapore :Springer Nature Singapore :2023. - x, 219 p. :ill., digital ;24 cm. - Machine learning: foundations, methodologies, and applications,2730-9916. - Machine learning: foundations, methodologies, and applications..

Chapter 1.Introduction -- Chapter 2. Overview and Application-driven Motivations of Evolutionary Multitasking -- Chapter 3.The Multi-factorial Evolutionary Algorithm -- Chapter 4. Multi-factorial Evolutionary Algorithm with Adaptive Knowledge Transfer -- Chapter 5.Explicit Evolutionary Multi-task Optimization Algorithm -- Chapter 6.Evolutionary Multi-task Optimization for Generalized Vehicle Routing Problem With Occasional Drivers -- Chapter 7. Explicit Evolutionary Multi-task Optimization for Capacitated Vehicle Routing Problem -- Chapter 8. Multi-Space Evolutionary Search for Large Scale Single-Objective Optimization -- Chapter 9.Multi-Space Evolutionary Search for Large-scale Multi-Objective Optimization.

A remarkable facet of the human brain is its ability to manage multiple tasks with apparent simultaneity. Knowledge learned from one task can then be used to enhance problem-solving in other related tasks. In machine learning, the idea of leveraging relevant information across related tasks as inductive biases to enhance learning performance has attracted significant interest. In contrast, attempts to emulate the human brain's ability to generalize in optimization - particularly in population-based evolutionary algorithms - have received little attention to date. Recently, a novel evolutionary search paradigm, Evolutionary Multi-Task (EMT) optimization, has been proposed in the realm of evolutionary computation. In contrast to traditional evolutionary searches, which solve a single task in a single run, evolutionary multi-tasking algorithm conducts searches concurrently on multiple search spaces corresponding to different tasks or optimization problems, each possessing a unique function landscape. By exploiting the latent synergies among distinct problems, the superior search performance of EMT optimization in terms of solution quality and convergence speed has been demonstrated in a variety of continuous, discrete, and hybrid (mixture of continuous and discrete) tasks. This book discusses the foundations and methodologies of developing evolutionary multi-tasking algorithms for complex optimization, including in domains characterized by factors such as multiple objectives of interest, high-dimensional search spaces and NP-hardness.

ISBN: 9789811956508$q(electronic bk.)

Standard No.: 10.1007/978-981-19-5650-8doiSubjects--Topical Terms:

231709
Evolutionary computation.

LC Class. No.: QA76.618

Dewey Class. No.: 006.3823

Evolutionary multi-task optimizationfoundations and methodologies /
LDR:03357nmm a2200337 a 4500 001 642513
003 DE-He213
005 20230329144203.0
006 m d
007 cr nn 008maaau
008 231123s2023 si s 0 eng d
020 $a 9789811956508$q(electronic bk.)
020 $a 9789811956492$q(paper)
024 7 $a 10.1007/978-981-19-5650-8 $2 doi
035 $a 978-981-19-5650-8
040 $a GP $c GP
041 0 $a eng
050 4 $a QA76.618
072 7 $a UYQ $2 bicssc
072 7 $a COM004000 $2 bisacsh
072 7 $a UYQ $2 thema
082 0 4 $a 006.3823 $2 23
090 $a QA76.618 $b .E93 2023
245 0 0 $a Evolutionary multi-task optimization $h [electronic resource] : $b foundations and methodologies / $c by Liang Feng ... [et al.].
260 $a Singapore : $b Springer Nature Singapore : $b Imprint: Springer, $c 2023.
300 $a x, 219 p. : $b ill., digital ; $c 24 cm.
490 1 $a Machine learning: foundations, methodologies, and applications, $x 2730-9916
505 0 $a Chapter 1.Introduction -- Chapter 2. Overview and Application-driven Motivations of Evolutionary Multitasking -- Chapter 3.The Multi-factorial Evolutionary Algorithm -- Chapter 4. Multi-factorial Evolutionary Algorithm with Adaptive Knowledge Transfer -- Chapter 5.Explicit Evolutionary Multi-task Optimization Algorithm -- Chapter 6.Evolutionary Multi-task Optimization for Generalized Vehicle Routing Problem With Occasional Drivers -- Chapter 7. Explicit Evolutionary Multi-task Optimization for Capacitated Vehicle Routing Problem -- Chapter 8. Multi-Space Evolutionary Search for Large Scale Single-Objective Optimization -- Chapter 9.Multi-Space Evolutionary Search for Large-scale Multi-Objective Optimization.
520 $a A remarkable facet of the human brain is its ability to manage multiple tasks with apparent simultaneity. Knowledge learned from one task can then be used to enhance problem-solving in other related tasks. In machine learning, the idea of leveraging relevant information across related tasks as inductive biases to enhance learning performance has attracted significant interest. In contrast, attempts to emulate the human brain's ability to generalize in optimization - particularly in population-based evolutionary algorithms - have received little attention to date. Recently, a novel evolutionary search paradigm, Evolutionary Multi-Task (EMT) optimization, has been proposed in the realm of evolutionary computation. In contrast to traditional evolutionary searches, which solve a single task in a single run, evolutionary multi-tasking algorithm conducts searches concurrently on multiple search spaces corresponding to different tasks or optimization problems, each possessing a unique function landscape. By exploiting the latent synergies among distinct problems, the superior search performance of EMT optimization in terms of solution quality and convergence speed has been demonstrated in a variety of continuous, discrete, and hybrid (mixture of continuous and discrete) tasks. This book discusses the foundations and methodologies of developing evolutionary multi-tasking algorithms for complex optimization, including in domains characterized by factors such as multiple objectives of interest, high-dimensional search spaces and NP-hardness.
650 0 $a Evolutionary computation. $3 231709
650 0 $a Machine learning. $3 188639
650 0 $a Mathematical optimization. $3 183292
650 1 4 $a Artificial Intelligence. $3 212515
650 2 4 $a Optimization. $3 274084
650 2 4 $a Computational Intelligence. $3 338479
700 1 $a Feng, Liang. $3 893825
710 2 $a SpringerLink (Online service) $3 273601
773 0 $t Springer Nature eBook
830 0 $a Machine learning: foundations, methodologies, and applications. $3 911919
856 4 0 $u https://doi.org/10.1007/978-981-19-5650-8
950 $a Computer Science (SpringerNature-11645)