Overview
- Explores advanced topics in deep learning encompassing transformer models, control theory, and graph neural networks
- Presents detailed mathematical descriptions and algorithms for generative pre-trained models, such as GPTs
- Serves as a valuable reference book for postgraduate and PhD students
Part of the book series: Texts in Computer Science (TCS)
Access this book
Tax calculation will be finalised at checkout
Other ways to access
About this book
The first edition of this textbook was published in 2021. Over the past two years, we have invested in enhancing all aspects of deep learning methods to ensure the book is comprehensive and impeccable. Taking into account feedback from our readers and audience, the author has diligently updated this book.
The second edition of this textbook presents control theory, transformer models, and graph neural networks (GNN) in deep learning. We have incorporated the latest algorithmic advances and large-scale deep learning models, such as GPTs, to align with the current research trends. Through the second edition, this book showcases how computational methods in deep learning serve as a dynamic driving force in this era of artificial intelligence (AI).
This book is intended for research students, engineers, as well as computer scientists with interest in computational methods in deep learning. Furthermore, it is also well-suited for researchers exploring topics such as machine intelligence, robotic control, and related areas.
Keywords
- Deep Learning
- Machine Learning
- Pattern Analysis
- Manifold Learning
- Machine Vision
- Reinforcement Learning
- Natural Language Processing
- Autoencoder
- Generative Adversarial Networks
- Transfer Learning
- Time-Series Analysis
- Calculus
- Linear Algebra
- Numerical Analysis
- Tensor Algebra
- Graphical Models
- Information Theory
- Optimization
- Functional Analysis
- Basic Algebra
Table of contents (7 chapters)
Authors and Affiliations
About the author
Wei Qi Yan is Director of Institute of Robotics & Vision (IoRV) at Auckland University of Technology (AUT) in New Zealand (NZ). Dr. Yan's research interests encompass deep learning, intelligent surveillance, computer vision, and multimedia computing. His expertise lies in computational mathematics, applied mathematics, computer science, and computer engineering. He holds the positions of Chief Technology Officer (CTO) of Screen 2 Script Limited (NZ) and Director and Chief Scientist of the Joint Laboratory between AUT and Shandong Academy of Sciences China (NZ). Dr. Yan also serves as Chair of ACM Multimedia Chapter of New Zealand and is Member of the ACM. Additionally, he is Senior Member of the IEEE and TC Member of the IEEE. In 2022, Dr. Yan was recognized as one of the world’s top 2% cited scientists by Stanford University.
Bibliographic Information
Book Title: Computational Methods for Deep Learning
Book Subtitle: Theory, Algorithms, and Implementations
Authors: Wei Qi Yan
Series Title: Texts in Computer Science
DOI: https://doi.org/10.1007/978-981-99-4823-9
Publisher: Springer Singapore
eBook Packages: Computer Science, Computer Science (R0)
Copyright Information: The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023
Hardcover ISBN: 978-981-99-4822-2Published: 16 September 2023
eBook ISBN: 978-981-99-4823-9Published: 15 September 2023
Series ISSN: 1868-0941
Series E-ISSN: 1868-095X
Edition Number: 2
Number of Pages: XX, 222
Number of Illustrations: 4 b/w illustrations, 36 illustrations in colour
Topics: Machine Learning, Mathematical Models of Cognitive Processes and Neural Networks, Mathematics of Computing, Computer Imaging, Vision, Pattern Recognition and Graphics, Artificial Intelligence