Название: Math Optimization for Artificial Intelligence: Heuristic and Metaheuristic Methods for Robotics and Machine Learning
Автор: Umesh Kumar Lilhore, Vishal Dutt, T. Ananth Kumar, Martin Margala, Kaamran Raahemifar
Издательство: De Gruyter
Год: 2025
Страниц: 644
Язык: английский
Формат: epub
Размер: 19.4 MB

The book presents powerful optimization approaches for integrating Artificial Intelligence (AI) into daily life.

This book explores how heuristic and metaheuristic methodologies have revolutionized the fields of robotics and Machine Learning (ML). The book covers the wide range of tools and methods that have emerged as part of the AI revolution, from state-of-the-art decision-making algorithms for robots to data-driven Machine Learning models. Each chapter offers a meticulous examination of the theoretical foundations and practical applications of mathematical optimization, helping readers understand how these methods are transforming the field of technology.

Today, Artificial Intelligence (AI) is applied in a variety of sectors, from healthcare to finance. AI is the technique of training an algorithm on a computer or a robot to think critically, similar to a human mind. AI is developed by studying the patterns in the human brain and by analysing the cognitive process. Optimization is one of the most often used techniques in many subfields of AI. Finding the optimal answer to a problem from a range of potential answers is the goal of optimization strategies. To minimize the amount of work needed or boost the targeted benefit, optimization is the process of maximizing or minimizing an objective function. The integration of AI with optimization methodologies facilitates the creation of intelligent systems that can effectively tackle intricate challenges in several fields. Swarm Intelligence (SI) is a method of artificial or natural intelligence. It offers robust performance and effective parallel global optimization features. It is a technique in which agents cooperate with one another and their surroundings in order to accomplish a shared objective. This leads to the sophisticated collective behaviour through local interactions and basic principles. The behavioural traits, evolutionary rules, and thought processes of insects, birds, natural events, and other biological populations are all simulated by SI systems. SI optimization has the potential to tackle complicated issues that are challenging to handle with conventional optimization methods. It is a key benefit of SI. They are extremely scalable and can be applied to address problems of various sizes and levels of complexity. The chapter highlights SI’s potential, limitations, and applications in AI. It is also examining challenges and future directions of SI optimization. A brief description of the particle swarm algorithm, genetic algorithms, ant-colony algorithm, and bee-colony algorithm is provided along with their optimization techniques.

This book is an invaluable resource for researchers, practitioners, and students. It makes AI optimization accessible and comprehensible, equipping the next generation of innovators with the knowledge and skills to further advance robotics and Machine Learning. While Artificial Intelligence constantly evolves, this book sheds light on the path ahead.






ОТСУТСТВУЕТ ССЫЛКА/ НЕ РАБОЧАЯ ССЫЛКА ЕСТЬ РЕШЕНИЕ, ПИШЕМ СЮДА!