Deep Learning: From Algorithmic Essence to Industrial Practice introduces the fundamental theories of deep learning, engineering practices, and their deployment and application in the industry. This book provides a detailed explanation of classic convolutional neural networks, recurrent neural networks, and transformer networks based on self-attention mechanisms, along with their variants, combining code demonstrations. Additionally, this book covers the applications of these models in areas including image classification, object detection, and semantic segmentation. This book also considers advancements in deep reinforcement learning and generative adversarial networks making it suitable for graduate and senior undergraduate students with backgrounds in computer science, automation, electronics, communications, mathematics, and physics, as well as professional technical personnel who wish to work or are preparing to transition into the field of artificial intelligence
The code for book may be accessed by visiting the companion website: https://www.
elsevier.com/books-and-journals/book-companion/9780443439544
1. Title of Book - p. i 2. Cover image - p. i 3. Title page - p. ii 4. Table of Contents - p. iii 5. Copyright - p. iv 6. About the authors - p. ix 7. Preface - p. xi 8. Overview - p. xiii 9. 1. Neural networks∗ - p. 1 10. 2. Convolutional neural networks—Image classification and object detection∗ - p. 51 11. 3. Convolutional neural networks—Semantic segmentation∗ - p. 103 12. 4. Recurrent neural networks∗ - p. 155 13. 5. Distributed deep learning systems∗ - p. 191 14. Chapter 6. Frontiers of deep learning∗ - p. 215 15. 7. Special lectures∗ - p. 257 16. 8. Transformer and its companions∗ - p. 301 17. 9. Core practices∗ - p. 369 18. 10. Deep learning inference systems∗ - p. 427 19. Index - p. 453
Deep Learning: From Algorithmic Essence to Industrial Practice introduces the fundamental theories of deep learning, engineering practices, and their deployment and application in the industry. This book provides a detailed explanation of classic convolutional neural networks, recurrent neural networks, and transformer networks based on self-attention mechanisms, along with their variants, combining code demonstrations. Additionally, this book covers the applications of these models in areas including image classification, object detection, and semantic segmentation. This book also considers advancements in deep reinforcement learning and generative adversarial networks making it suitable for graduate and senior undergraduate students with backgrounds in computer science, automation, electronics, communications, mathematics, and physics, as well as professional technical personnel who wish to work or are preparing to transition into the field of artificial intelligence
The code for book may be accessed by visiting the companion website: https://www.
elsevier.com/books-and-journals/book-companion/9780443439544
1. Title of Book - p. i 2. Cover image - p. i 3. Title page - p. ii 4. Table of Contents - p. iii 5. Copyright - p. iv 6. About the authors - p. ix 7. Preface - p. xi 8. Overview - p. xiii 9. 1. Neural networks∗ - p. 1 10. 2. Convolutional neural networks—Image classification and object detection∗ - p. 51 11. 3. Convolutional neural networks—Semantic segmentation∗ - p. 103 12. 4. Recurrent neural networks∗ - p. 155 13. 5. Distributed deep learning systems∗ - p. 191 14. Chapter 6. Frontiers of deep learning∗ - p. 215 15. 7. Special lectures∗ - p. 257 16. 8. Transformer and its companions∗ - p. 301 17. 9. Core practices∗ - p. 369 18. 10. Deep learning inference systems∗ - p. 427 19. Index - p. 453
