東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁 到查詢結果 [ subject:"Machine learning- Mathematics." ]

切換: 標籤 | MARC模式 | ISBD

General-purpose optimization through...

Lockett, Alan J.

FindBook

Google Book

Amazon

博客來

General-purpose optimization through information maximization

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	General-purpose optimization through information maximization/ by Alan J. Lockett.
作者:	Lockett, Alan J.
出版者:	Berlin, Heidelberg :Springer Berlin Heidelberg : : 2020.,
面頁冊數:	xviii, 561 p. :ill., digital ;24 cm.
內容註:	Introduction -- Review of Optimization Methods -- Functional Analysis of Optimization -- A Unified View of Population-Based Optimizers -- Continuity of Optimizers -- The Optimization Process -- Performance Analysis -- Performance Experiments -- No Free Lunch Does Not Prevent General Optimization -- The Geometry of Optimization and the Optimization Game -- The Evolutionary Annealing Method -- Evolutionary Annealing In Euclidean Space -- Neuroannealing -- Discussion and Future Work -- Conclusion -- App. A, Performance Experiment Results -- App. B, Automated Currency Exchange Trading.
Contained By:	Springer Nature eBook
標題:	Mathematical optimization. -
電子資源:	https://doi.org/10.1007/978-3-662-62007-6
ISBN:	9783662620076

General-purpose optimization through information maximization
Lockett, Alan J.

General-purpose optimization through information maximization[electronic resource] /by Alan J. Lockett. - Berlin, Heidelberg :Springer Berlin Heidelberg :2020. - xviii, 561 p. :ill., digital ;24 cm. - Natural computing series,1619-7127. - Natural computing series..

Introduction -- Review of Optimization Methods -- Functional Analysis of Optimization -- A Unified View of Population-Based Optimizers -- Continuity of Optimizers -- The Optimization Process -- Performance Analysis -- Performance Experiments -- No Free Lunch Does Not Prevent General Optimization -- The Geometry of Optimization and the Optimization Game -- The Evolutionary Annealing Method -- Evolutionary Annealing In Euclidean Space -- Neuroannealing -- Discussion and Future Work -- Conclusion -- App. A, Performance Experiment Results -- App. B, Automated Currency Exchange Trading.

This book examines the mismatch between discrete programs, which lie at the center of modern applied mathematics, and the continuous space phenomena they simulate. The author considers whether we can imagine continuous spaces of programs, and asks what the structure of such spaces would be and how they would be constituted. He proposes a functional analysis of program spaces focused through the lens of iterative optimization. The author begins with the observation that optimization methods such as Genetic Algorithms, Evolution Strategies, and Particle Swarm Optimization can be analyzed as Estimation of Distributions Algorithms (EDAs) in that they can be formulated as conditional probability distributions. The probabilities themselves are mathematical objects that can be compared and operated on, and thus many methods in Evolutionary Computation can be placed in a shared vector space and analyzed using techniques of functional analysis. The core ideas of this book expand from that concept, eventually incorporating all iterative stochastic search methods, including gradient-based methods. Inspired by work on Randomized Search Heuristics, the author covers all iterative optimization methods and not just evolutionary methods. The No Free Lunch Theorem is viewed as a useful introduction to the broader field of analysis that comes from developing a shared mathematical space for optimization algorithms. The author brings in intuitions from several branches of mathematics such as topology, probability theory, and stochastic processes and provides substantial background material to make the work as self-contained as possible. The book will be valuable for researchers in the areas of global optimization, machine learning, evolutionary theory, and control theory.

ISBN: 9783662620076

Standard No.: 10.1007/978-3-662-62007-6doiSubjects--Topical Terms:

517763
Mathematical optimization.

LC Class. No.: QA402.5

Dewey Class. No.: 519.6

General-purpose optimization through information maximization
LDR:03433nmm a2200349 a 4500 001 2255754
003 DE-He213
005 20200816084800.0
006 m d
007 cr nn 008maaau
008 220420s2020 gw s 0 eng d
020 $a 9783662620076 $q (electronic bk.)
020 $a 9783662620069 $q (paper)
024 7 $a 10.1007/978-3-662-62007-6 $2 doi
035 $a 978-3-662-62007-6
040 $a GP $c GP
041 0 $a eng
050 4 $a QA402.5
072 7 $a UY $2 bicssc
072 7 $a COM014000 $2 bisacsh
072 7 $a UY $2 thema
072 7 $a UYA $2 thema
082 0 4 $a 519.6 $2 23
090 $a QA402.5 $b .L815 2020
100 1 $a Lockett, Alan J. $3 3525473
245 1 0 $a General-purpose optimization through information maximization $h [electronic resource] / $c by Alan J. Lockett.
260 $a Berlin, Heidelberg : $b Springer Berlin Heidelberg : $b Imprint: Springer, $c 2020.
300 $a xviii, 561 p. : $b ill., digital ; $c 24 cm.
490 1 $a Natural computing series, $x 1619-7127
505 0 $a Introduction -- Review of Optimization Methods -- Functional Analysis of Optimization -- A Unified View of Population-Based Optimizers -- Continuity of Optimizers -- The Optimization Process -- Performance Analysis -- Performance Experiments -- No Free Lunch Does Not Prevent General Optimization -- The Geometry of Optimization and the Optimization Game -- The Evolutionary Annealing Method -- Evolutionary Annealing In Euclidean Space -- Neuroannealing -- Discussion and Future Work -- Conclusion -- App. A, Performance Experiment Results -- App. B, Automated Currency Exchange Trading.
520 $a This book examines the mismatch between discrete programs, which lie at the center of modern applied mathematics, and the continuous space phenomena they simulate. The author considers whether we can imagine continuous spaces of programs, and asks what the structure of such spaces would be and how they would be constituted. He proposes a functional analysis of program spaces focused through the lens of iterative optimization. The author begins with the observation that optimization methods such as Genetic Algorithms, Evolution Strategies, and Particle Swarm Optimization can be analyzed as Estimation of Distributions Algorithms (EDAs) in that they can be formulated as conditional probability distributions. The probabilities themselves are mathematical objects that can be compared and operated on, and thus many methods in Evolutionary Computation can be placed in a shared vector space and analyzed using techniques of functional analysis. The core ideas of this book expand from that concept, eventually incorporating all iterative stochastic search methods, including gradient-based methods. Inspired by work on Randomized Search Heuristics, the author covers all iterative optimization methods and not just evolutionary methods. The No Free Lunch Theorem is viewed as a useful introduction to the broader field of analysis that comes from developing a shared mathematical space for optimization algorithms. The author brings in intuitions from several branches of mathematics such as topology, probability theory, and stochastic processes and provides substantial background material to make the work as self-contained as possible. The book will be valuable for researchers in the areas of global optimization, machine learning, evolutionary theory, and control theory.
650 0 $a Mathematical optimization. $3 517763
650 0 $a Machine learning $x Mathematics. $3 3442737
650 0 $a Functional analysis. $3 531838
650 1 4 $a Theory of Computation. $3 892514
650 2 4 $a Artificial Intelligence. $3 769149
650 2 4 $a Optimization. $3 891104
650 2 4 $a Mathematics of Computing. $3 891213
710 2 $a SpringerLink (Online service) $3 836513
773 0 $t Springer Nature eBook
830 0 $a Natural computing series. $3 2057566
856 4 0 $u https://doi.org/10.1007/978-3-662-62007-6
950 $a Computer Science (SpringerNature-11645)