Deep Learning: Fundamentals, Theory and Applications

1. Front Matter

   Pages i-vii

   PDF

2. Introduction to Deep Density Models with Latent Variables

   • Xi Yang, Kaizhu Huang, Rui Zhang, Amir Hussain

   Pages 1-29

3. Deep RNN Architecture: Design and Evaluation

   • Tonghua Su, Li Sun, Qiu-Feng Wang, Da-Han Wang

   Pages 31-55

4. Deep Learning Based Handwritten Chinese Character and Text Recognition

   • Xu-Yao Zhang, Yi-Chao Wu, Fei Yin, Cheng-Lin Liu

   Pages 57-88

5. Deep Learning and Its Applications to Natural Language Processing

   • Haiqin Yang, Linkai Luo, Lap Pong Chueng, David Ling, Francis Chin

   Pages 89-109

6. Deep Learning for Natural Language Processing

   • Jiajun Zhang, Chengqing Zong

   Pages 111-138

7. Oceanic Data Analysis with Deep Learning Models

   • Guoqiang Zhong, Li-Na Wang, Qin Zhang, Estanislau Lima, Xin Sun, Junyu Dong et al.

   Pages 139-160

8. Back Matter

   Pages 161-163

   PDF

The purpose of this edited volume is to provide a comprehensive overview on the fundamentals of deep learning, introduce the widely-used learning architectures and algorithms, present its latest theoretical progress, discuss the most popular deep learning platforms and data sets, and describe how many deep learning methodologies have brought great breakthroughs in various applications of text, image, video, speech and audio processing.

Deep learning (DL) has been widely considered as the next generation of machine learning methodology. DL attracts much attention and also achieves great success in pattern recognition, computer vision, data mining, and knowledge discovery due to its great capability in learning high-level abstract features from vast amount of data. This new book will not only attempt to provide a general roadmap or guidance to the current deep learning methodologies, but also present the challenges and envision new perspectives which may lead to further breakthroughs in this field.

This book will serve as a useful reference for senior (undergraduate or graduate) students in computer science, statistics, electrical engineering, as well as others interested in studying or exploring the potential of exploiting deep learning algorithms. It will also be of special interest to researchers in the area of AI, pattern recognition, machine learning and related areas, alongside engineers interested in applying deep learning models in existing or new practical applications.

• Neural networks
• Deep representation
• Learning
• Optimization
• Artificial intelligence
• Cognitively-inspired methods

“This reviewer maintains skepticism about how accessible this book is to the typical undergraduate. However, a senior level graduate student may find incredible value in the exposition. The practitioner may enjoy this text as a companion to an existing library as well as a muse for modifying current methodologies by those cited in the research papers.” (Mannan Shah, MAA Reviews, September 22, 2019)

• Xi’an Jiaotong-Liverpool University, Suzhou, China

  Kaizhu Huang, Qiu-Feng Wang, Rui Zhang

• School of Computing, Edinburgh Napier University, Edinburgh, UK

  Amir Hussain

Policies and ethics