Название: Computational Mechanics with Deep Learning: An Introduction
Автор: Genki Yagawa, Atsuya Oishi
Издательство: Springer
Год: 2023
Страниц: 408
Язык: английский
Формат: pdf (true)
Размер: 10.1 MB

This book is intended for students, engineers, and researchers interested in both computational mechanics and Deep Learning. It presents the mathematical and computational foundations of Deep Learning (DL) with detailed mathematical formulas in an easy-to-understand manner. It also discusses various applications of Deep Learning in Computational Mechanics, with detailed explanations of the Computational Mechanics fundamentals selected there. Sample programs are included for the reader to try out in practice. This book is therefore useful for a wide range of readers interested in computational mechanics and Deep Learning.

The present book is written from the standpoint of integrating computational mechanics and deep learning, consisting of three parts: Part I (Chaps. 1–3) covers the basics, Part II (Chaps. 4–8) covers several applications of deep learning to computational mechanics with detailed descriptions of the fields of computational mechanics to which deep learning is applied, and Part III (Chaps. 9–10) describes programming, where the program codes for both computational mechanics and deep learning are discussed in detail. The authors have tried to make the program not a black box, but a useful tool for readers to fully understand and handle the processing. The contents of each chapter are summarized as follows:

Part I Fundamentals:
In Chap. 1, the importance of deep learning in computational mechanics is given first and then the development process of deep learning is reviewed. In addition, various new methods used in deep learning are introduced in an easy-to-understand manner.

Chapter 2 is devoted to the mathematical aspects of deep learning. It discusses the forward and backward propagations of typical network structures in deep learning, such as fully connected feedforward neural networks and convolutional neural networks,using mathematical formulas with examples,and also learning acceleration and regularization methods.