Mathematics Transfer Learning / Kota MATSUI / Wataru KUMAGAI

Product description ※Please note that product information is not in full comprehensive meaning because of the machine translation.

Mathematics
Machine Learning Professional Series / ★ Truly Bible! ★ Transfer learning is a way to handle requests and problems that are difficult to solve with conventional machine learning methods. Since the advent of deep learning, it has become easier to use pre-learned models, and transfer learning has become widely used. This book provides detailed explanations of the basic concepts of transfer learning, domain adaptation, pre-learned models, knowledge distillation, multi-task learning, meta-learning, and continuous learning. Let's start with this one book! [Main Contents] Part 1 Introduction to Transfer Learning Chapter 1 From Machine Learning to Transfer Learning Chapter 2 Basic Concepts of Transfer Learning Chapter 2 Fundamentals of Transfer Learning Chapter 3 Theory of Domain Adaptation Chapter 4 Fundamentals of Data-Based Domain Adaptation Chapter 5 Theory of Domain Adaptation Chapter 4 Fundamentals of Data-Based Domain Adaptation Chapter 5 Evolution of Model-Based Domain Adaptation Chapter 6 Pre-Learned Models Part 3 Transfer Learning Chapter 7 Knowledge distillation Chapter 8 Multi-Task Learning Chapter 9 Meta-Learning Chapter 10 Small-Number Shot Learning Chapter 11 Domain Generalization Chapter 12 Continuous Learning Chapter 13 Transfer Learning in Reinforcement Learning Appendix A Fundamentals of Deep Neural Networks and Generative Models