0
Your cart

Your cart is empty

Browse All Departments
  • All Departments
Price
  • R5,000 - R10,000 (2)
  • -
Status
Brand

Showing 1 - 2 of 2 matches in All Departments

General-Purpose Optimization Through Information Maximization (Hardcover, 1st ed. 2020): Alan J. Lockett General-Purpose Optimization Through Information Maximization (Hardcover, 1st ed. 2020)
Alan J. Lockett
R5,690 Discovery Miles 56 900 Ships in 10 - 15 working days

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.

General-Purpose Optimization Through Information Maximization (Paperback, 1st ed. 2020): Alan J. Lockett General-Purpose Optimization Through Information Maximization (Paperback, 1st ed. 2020)
Alan J. Lockett
R5,661 Discovery Miles 56 610 Ships in 10 - 15 working days

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.

Free Delivery
Pinterest Twitter Facebook Google+
You may like...
A History Of South Africa - From The…
Fransjohan Pretorius Paperback R765 Discovery Miles 7 650
Onion Raising
James J.H. Gregory Paperback R211 Discovery Miles 2 110
Pneumatologia - Or, a Discourse…
John Owen Paperback R600 Discovery Miles 6 000
The Lost Prince Of The ANC - The Life…
Mandla J. Radebe Paperback R521 Discovery Miles 5 210
The Origin of the Virus - The hidden…
Paolo Barnard, Steven Quay, … Paperback R365 Discovery Miles 3 650
Literacy in Teacher Preparation and…
Patrick M. Jenlink Hardcover R3,000 Discovery Miles 30 000
Food Safety in the Middle East
Ioannis Savvaidis, Tareq Osaili Paperback R3,709 Discovery Miles 37 090
The Sunday School Hand-Book
Erwin. House Paperback R566 Discovery Miles 5 660
The Works of Isaac Penington - a…
Isaac Penington Paperback R751 Discovery Miles 7 510
Lectures on Political Atheism and…
Lyman Beecher Paperback R639 Discovery Miles 6 390

 

Partners