First-Order and Stochastic Optimization Methods for Machine Learning, Lan Guanghui
Автор: Oksendal Название: Stochastic Differential Equations ISBN: 3540047581 ISBN-13(EAN): 9783540047582 Издательство: Springer Рейтинг: Цена: 8223.00 р. Наличие на складе: Есть (1 шт.) Описание: Gives an introduction to the basic theory of stochastic calculus and its applications. This book offers examples in order to motivate and illustrate the theory and show its importance for many applications in for example economics, biology and physics.
Автор: Sen Название: Global Optimization Methods in Geophysical Inversion ISBN: 1107011906 ISBN-13(EAN): 9781107011908 Издательство: Cambridge Academ Рейтинг: Цена: 14525.00 р. 20750.00-30% Наличие на складе: Есть (1 шт.) Описание: This up-to-date new edition provides an overview of global optimization methods, and includes succinct descriptions of background theory, advanced concepts and examples of geophysical inversion, enabling readers to formulate their own applications. A valuable resource for researchers, graduate students and professionals in geophysics, inverse theory, exploration geoscience and engineering.
Описание: This book covers not only foundational materials but also the most recent progresses made during the past few years on the area of machine learning algorithms.
Описание: This book addresses the uncertainties of wind power modeled as interval numbers and assesses the physical modeling and methods for interval power flow, interval economic dispatch and interval robust economic dispatch.
Описание: The acceleration of first-order optimization algorithms is crucial for the efficiency of machine learning.Written by leading experts in the field, this book provides a comprehensive introduction to, and state-of-the-art review of accelerated first-order optimization algorithms for machine learning.
Описание: 1. Optimal Control under Stochastic Uncertainty.- 2. Stochastic Optimization of Regulators.- 3. Optimal Open-Loop Control of Dynamic Systems under Stochastic Uncertainty.- 4. Construction of feedback control by means of homotopy methods.- 5. Constructions of Limit State Functions.- 6. Random Search Procedures for Global Optimization.- 7. Controlled Random Search under Uncertainty.- 8. Controlled Random Search Procedures for Global Optimization.- 9. Mathematical Model of Random Search Methods and Elementary Properties.- 10. Special Random Search Methods.- 11. Accessibility Theorems.- 12. Convergence Theorems.- 13. Convergence of Stationary Random Search Methods for Positive Success Probability.- 14. Random Search Methods of convergence order U(n-").- 15. Random Search Methods with a Linear Rate of Convergence.- 16. Success/Failure-driven Random Direction Procedures.- 17. Hybrid Methods.- 18. Solving optimization problems under stochastic uncertainty by Random Search Methods(RSM).
Автор: Marti, Kurt Название: Stochastic optimization methods ISBN: 3662500124 ISBN-13(EAN): 9783662500125 Издательство: Springer Рейтинг: Цена: 18167.00 р. Наличие на складе: Есть у поставщика Поставка под заказ.
Описание: Stochastic Optimization Methods.- Optimal Control Under Stochastic Uncertainty.- Stochastic Optimal Open-Loop Feedback Control.- Adaptive Optimal Stochastic Trajectory Planning and Control (AOSTPC).- Optimal Design of Regulators.- Expected Total Cost Minimum Design of Plane Frames.- Stochastic Structural Optimization with Quadratic Loss Functions.- Maximum Entropy Techniques.
Описание: The book reviews mechanical engineering design optimization using stochastic methods. It introduces students and design engineers to practical aspects of complicated mathematical optimization procedures, and outlines steps for wide range of selected engineering design problems.
Автор: Tor Lattimore, Csaba Szepesvari Название: Bandit Algorithms ISBN: 1108486827 ISBN-13(EAN): 9781108486828 Издательство: Cambridge Academ Рейтинг: Цена: 6970.00 р. Наличие на складе: Есть у поставщика Поставка под заказ.
Описание: Decision-making in the face of uncertainty is a challenge in machine learning, and the multi-armed bandit model is a common framework to address it. This comprehensive introduction is an excellent reference for established researchers and a resource for graduate students interested in exploring stochastic, adversarial and Bayesian frameworks.
Автор: Chauhan Vinod Kumar Название: Stochastic Optimization for Large-Scale Machine Learning ISBN: 1032131756 ISBN-13(EAN): 9781032131757 Издательство: Taylor&Francis Рейтинг: Цена: 24499.00 р. Наличие на складе: Есть у поставщика Поставка под заказ.
Описание: Stochastic Optimization for Large-scale Machine Learning identifies different areas of improvement and recent research directions to tackle the challenge. Developed optimisation techniques are also explored to improve machine learning algorithms based on data access and on first and second order optimisation methods.
Stochastic global optimization methods and applications to chemical, biochemical, pharmaceutical and environmental processes presents various algorithms that include the genetic algorithm, simulated annealing, differential evolution, ant colony optimization, tabu search, particle swarm optimization, artificial bee colony optimization, and cuckoo search algorithm. The design and analysis of these algorithms is studied by applying them to solve various base case and complex optimization problems concerning chemical, biochemical, pharmaceutical, and environmental engineering processes.
Design and implementation of various classical and advanced optimization strategies to solve a wide variety of optimization problems makes this book beneficial to graduate students, researchers, and practicing engineers working in multiple domains. This book mainly focuses on stochastic, evolutionary, and artificial intelligence optimization algorithms with a special emphasis on their design, analysis, and implementation to solve complex optimization problems and includes a number of real applications concerning chemical, biochemical, pharmaceutical, and environmental engineering processes.
Описание: 1. Optimal Control under Stochastic Uncertainty.- 2. Stochastic Optimization of Regulators.- 3. Optimal Open-Loop Control of Dynamic Systems under Stochastic Uncertainty.- 4. Construction of feedback control by means of homotopy methods.- 5. Constructions of Limit State Functions.- 6. Random Search Procedures for Global Optimization.- 7. Controlled Random Search under Uncertainty.- 8. Controlled Random Search Procedures for Global Optimization.- 9. Mathematical Model of Random Search Methods and Elementary Properties.- 10. Special Random Search Methods.- 11. Accessibility Theorems.- 12. Convergence Theorems.- 13. Convergence of Stationary Random Search Methods for Positive Success Probability.- 14. Random Search Methods of convergence order U(n-").- 15. Random Search Methods with a Linear Rate of Convergence.- 16. Success/Failure-driven Random Direction Procedures.- 17. Hybrid Methods.- 18. Solving optimization problems under stochastic uncertainty by Random Search Methods(RSM).
ООО "Логосфера " Тел:+7(495) 980-12-10 www.logobook.ru
