Название: Artificial Intelligence in Material Science: Advances
Автор: Mohamed Arezki Mellal
Издательство: CRC Press
Год: 2025
Страниц: 277
Язык: английский
Формат: pdf (true), epub
Размер: 24.3 MB

Artificial Intelligence (AI) in the form of Machine Learning and nature-inspired optimization algorithms are vastly used in material science. These techniques improve many quality metrics, such as reliability and ergonomics.

This book highlights the recent challenges in this field and helps readers to understand the subject and develop future works. It reviews the latest methods and applications of AI in material science. It covers a wide range of topics, including Material processing; Properties prediction; Conventional machining, such as turning, boring, grinding, and milling; non-conventional machining, such as electrical discharge machining, electrochemical machining, laser machining, plasma machining, ultrasonic machining, chemical machining, and water-jet machining; Machine tools, such as programming, design, and maintenance. AI techniques reviewed in the book include Machine learning, Fuzzy logic, Genetic algorithms, Particle swarm optimization, Cuckoo search, Grey wolf optimizer, and Ant colony optimization.

The Capter 1 makes two main contributions: (1) It comprehensively and perceptively summarises research achievements on Transfer Learning from the perspective of applications of Computational Intelligence, and it strategically clusters the Transfer Learning into four Computational Intelligence application domains; and (2) For each Computational Intelligence technique, it carefully analyses typical Transfer Learning frameworks and effectively identifies the specific requirements. It also covers some brand-new transfer learning techniques with computational intelligence and reveals their successful applications. This will help researchers and practitioners directly promote the popularisation and application of computational intelligence in transfer learning in various domains. Neural Network is a learning-based approach to problem-solving that draws inspiration from the structure and workings of the human brain. Many studies have demonstrated that neural networks outperform statistical approaches in conventional Machine Learning issues. This finding has inspired many academics, especially those working on challenging issues, to employ neural networks for transfer learning. Several neural network-based transfer learning techniques have been developed recently to solve the transfer learning issue. The Deep Neural Network, Multiple Tasks Neural Network, and Radial Basis Function Neural Network are three of the main Neural Network approaches discussed in this section with examples of how they are used in Transfer Learning.




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