In this book, we work for the contents for knowledge transfer from the viewpoint of machine intelligence. We adopt the methodology from graphical theory, mathematical models, algorithmic implementation as well as datasets preparation, programming, results analysis and evaluations. We start from understanding artificial neural networks with neurons and the activation functions, then explain the mechanism of deep learning using advanced mathematics. We especially emphasize on how to use TensorFlow and the latest MATLAB deep learning toolboxes for implementing deep learning algorithms. Before reading this book, we strongly encourage our readers to understand the knowledge of mathematics, especially those subjects like mathematical analysis, linear algebra, numerical analysis, optimizations, differential geometry, manifold, information theory as well as basic algebra, functional analysis, graphical models, etc. The computational knowledge will assist us not only in understanding this book and but also in relevant deep learning journal articles and conference papers. This book was written for research students and engineers as well as computer scientists who are interested in deep learning for theoretic research and analysis. More generally, this book is also helpful for those researchers who are interested in machine intelligence, pattern analysis, natural language processing, and machine vision.
Author(s): Wei Qi Yan
Series: Texts in Computer Science
Publisher: Springer
Year: 2021
Language: English
Pages: 130
City: Cham
Preface
Acknowledgements
Contents
About the Author
Symbols and Acronyms
1 Introduction
1.1 Introduction
1.2 Deep Learning
1.3 The Chronicle of Deep Learning
1.4 Our Deep Learning Projects
1.5 Awarded Work in Deep Learning
1.6 Questions
2 Deep Learning Platforms
2.1 Introduction
2.2 MATLAB for Deep Learning
2.3 TensorFlow for Deep Learning
2.4 Data Augmentation
2.5 Fundamental Mathematics
2.6 Questions
3 CNN and RNN
3.1 CNN and YOLO
3.1.1 R-CNN
3.1.2 Mask R-CNN
3.1.3 YOLO
3.1.4 SSD
3.1.5 DenseNets and ResNets
3.2 RNN and Time Series Analysis
3.3 HMM
3.3.1 RNN: Recurrent Neural Networks
3.3.2 Time Series Analysis
3.4 Functional Spaces
3.4.1 Metric Space
3.5 Vector Space
3.5.1 Normed Space
3.5.2 Hilbert Space
3.6 Questions
4 Autoencoder and GAN
4.1 Autoencoder
4.2 Regularizations and Autoencoders
4.3 Generative Adversarial Networks
4.4 Information Theory
4.5 Questions
5 Reinforcement Learning
5.1 Introduction
5.2 Bellman Equation
5.3 Deep Q-Learning
5.4 Optimization
5.5 Data Fitting
5.6 Questions
6 CapsNet and Manifold Learning
6.1 CapsNet
6.2 Manifold Learning
6.3 Questions
7 Boltzmann Machines
7.1 Boltzmann Machine
7.2 Restricted Boltzmann Machine
7.3 Deep Boltzmann Machine
7.4 Probabilistic Graphical Models
7.5 Questions
8 Transfer Learning and Ensemble Learning
8.1 Transfer Learning
8.1.1 Transfer Learning
8.1.2 Taskonomy
8.2 Siamese Neural Networks
8.3 Ensemble Learning
8.4 Important Work in Deep Learning
8.5 Awarded Work in Deep Learning
8.6 Questions
Glossary
Index
