| Description |
1 online resource (220 p.) |
| Series |
Machine Learning: Foundations, Methodologies, and Applications |
|
Machine learning: foundations, methodologies, and applications
|
| Contents |
Intro -- Preface -- Contents -- Part I Background -- 1 Introduction -- 1.1 Optimization -- 1.2 Evolutionary Optimization -- 1.3 Evolutionary Multi-Task Optimization -- 1.4 Organization of the Book -- 2 Overview and Application-Driven Motivations of Evolutionary Multitasking -- 2.1 An Overview of EMT Algorithms -- 2.2 EMT in Real-World Problems -- 2.2.1 Category 1: EMT in Data Science Pipelines -- 2.2.2 Category 2: EMT in Evolving Embodied Intelligence -- 2.2.3 Category 3: EMT in Unmanned Systems Planning -- 2.2.4 Category 4: EMT in Complex Design |
|
2.2.5 Category 5: EMT in Manufacturing, Operations Research -- 2.2.6 Category 6: EMT in Software and Services Computing -- Part II Evolutionary Multi-Task Optimization for Solving Continuous Optimization Problems -- 3 The Multi-Factorial Evolutionary Algorithm -- 3.1 Algorithm Design and Details -- 3.1.1 Multi-Factorial Optimization -- 3.1.2 Similarity and Difference Between Multi-factorial Optimization and Multi-Objective Optimization -- 3.1.3 The Multi-Factorial Evolutionary Algorithm -- 3.1.3.1 Population Initialization -- 3.1.3.2 Genetic Mechanisms -- 3.1.3.3 Selective Evaluation |
|
3.1.3.4 Selection Operation -- 3.1.3.5 Summarizing the Salient Features of the MFEA -- 3.2 Empirical Study -- 3.2.1 Multitasking Across Functions with Intersecting Optima -- 3.2.2 Multitasking Across Functions with Separated Optima -- 3.2.3 Discussions -- 3.3 Summary -- 4 Multi-Factorial Evolutionary Algorithm with Adaptive Knowledge Transfer -- 4.1 Algorithm Design and Details -- 4.1.1 Representative Crossover Operators for Continuous Optimization -- 4.1.2 Knowledge Transfer via Different Crossover Operators in MFEA -- 4.1.3 MFEA with Adaptive Knowledge Transfer |
|
4.1.3.1 Adaptive Assortative Mating and Adaptive Vertical Cultural Transmission -- 4.1.3.2 Adaptation of Transfer Crossover Indicators -- 4.2 Empirical Study -- 4.2.1 Experimental Setup -- 4.2.2 Performance Metric -- 4.2.3 Results and Discussions -- 4.2.3.1 Common Multi-Task Benchmarks -- 4.2.3.2 Complex Multi-Task Problems -- 4.2.4 Other Issues -- 4.3 Summary -- 5 Explicit Evolutionary Multi-Task Optimization Algorithm -- 5.1 Algorithm Design and Details -- 5.1.1 Denoising Autoencoder -- 5.1.2 The Explicit EMT Paradigm -- 5.1.2.1 Learning of Task Mapping |
|
5.1.2.2 Explicit Genetic Transfer Across Tasks -- 5.2 Empirical Study -- 5.2.1 Single-Objective Multi-Task Optimization -- 5.2.1.1 Experiment Setup -- 5.2.1.2 Results and Discussions -- 5.2.2 Multi-Objective Multi-Task Optimization -- 5.2.2.1 Experiment Setup -- 5.2.2.2 Results and Discussions -- 5.3 Summary -- Part III Evolutionary Multi-Task Optimization for Solving Combinatorial Optimization Problems -- 6 Evolutionary Multi-Task Optimization for Generalized Vehicle Routing Problem with Occasional Drivers |
| Summary |
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 brains 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 |
| Notes |
6.1 Vehicle Routing Problem with Heterogeneous Capacity, Time Window and Occasional Driver (VRPHTO) |
| Bibliography |
Includes bibliographical references |
| Notes |
Online resource; title from PDF title page (SpringerLink, viewed April 10, 2023) |
| Subject |
Evolutionary computation.
|
|
Machine learning.
|
|
Mathematical optimization.
|
|
Evolutionary computation
|
|
Machine learning
|
|
Mathematical optimization
|
| Form |
Electronic book
|
| Author |
Gupta, Abhishek
|
|
Tan, K. C.
|
|
Ong, Yew Soon.
|
| ISBN |
9789811956508 |
|
9811956502 |
|
