Computational Methods for Deep Learning: Theoretic, Practice and Applications

This textbook integrates concepts from deep learning, machine learning, and artificial neural networks and presents content progressively from easy to more complex, focusing on knowledge transfer from the viewpoint of machine intelligence. It adopts a methodology from graphical theory, mathematical models, and algorithmic implementation and covers datasets preparation, programming, results analysis, and evaluations. It is aimed at Computer Science research students and engineers, as well as scientists interested in deep learning for theoretic research and analysis.

Format: Hardback
Length: 134 pages
Publication date: 05 December 2020
Publisher: Springer Nature Switzerland AG

This groundbreaking textbook seamlessly integrates concepts from deep learning, machine learning, and artificial neural networks, presenting content in a progressive manner, starting from easy to more complex topics. Its content is organized around the theme of knowledge transfer from the perspective of machine intelligence. The book adopts a multidisciplinary approach, drawing from graphical theory, mathematical models, and algorithmic implementation. It also covers essential aspects such as dataset preparation, programming, results analysis, and evaluations.

Beginning with a foundational understanding of artificial neural networks, including neurons and activation functions, the book delves into the mechanism of deep learning, employing advanced mathematics to explain the process. It emphasizes the practical application of deep learning algorithms using popular tools like TensorFlow and the latest MATLAB deep-learning toolboxes.

As a prerequisite, readers are expected to have a solid foundation in mathematical analysis, linear algebra, numerical analysis, optimization, differential geometry, manifold, and information theory. This computational knowledge will serve as a valuable asset in comprehending the subject matter covered in this text/reference, as well as in relevant deep learning journal articles and conference papers.

This textbook/guide is specifically designed for Computer Science research students and engineers, as well as scientists interested in deep learning for theoretical research and analysis. It is also valuable for researchers who are interested in machine intelligence, pattern analysis, natural language processing, and machine vision.

Dr. Wei Qi Yan, an Associate Professor in the Department of Computer Science at Auckland University of Technology, New Zealand, is the author of this textbook. He has published several other notable works, including the Springer title, "Visual Cryptography for Image Processing."

Weight: 378g
Dimension: 160 x 241 x 17 (mm)
ISBN-13: 9783030610807
Edition number: 1st ed. 2021