Evolutionary Multi-Task Optimization

Foundations and Methodologies

Liang Feng, Yew Soon Ong, Kay Chen Tan, et al.

PDF
ca. 171,19
Amazon iTunes Thalia.de Weltbild.de Hugendubel Bücher.de ebook.de kobo Osiander Google Books Barnes&Noble bol.com Legimi yourbook.shop Kulturkaufhaus ebooks-center.de
* Affiliatelinks/Werbelinks
Hinweis: Affiliatelinks/Werbelinks
Links auf reinlesen.de sind sogenannte Affiliate-Links. Wenn du auf so einen Affiliate-Link klickst und über diesen Link einkaufst, bekommt reinlesen.de von dem betreffenden Online-Shop oder Anbieter eine Provision. Für dich verändert sich der Preis nicht.

Springer Nature Singapore img Link Publisher

Naturwissenschaften, Medizin, Informatik, Technik / Informatik

Beschreibung

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. 

Weitere Titel in dieser Kategorie
Cover Cyber Operations
Jerry M. Couretas
Cover Cyber Operations
Jerry M. Couretas

Kundenbewertungen

Schlagwörter

continuous optimization, knowledge learning, large-scale optimization, combinatorial optimization, optimization, knowledge transfer, evolutionary computation, artificial intelligence