Preface
What is deep learning for those who want to study physics? Is it completely different
from physics? Or is it really similar?
In recent years, machine learning, including deep learning, has begun to be used
in various physics studies. Why is that? Is knowing physics useful in machine
learning? Conversely, is knowing machine learning useful in physics?
This book is devoted to answers of these questions. Starting with basic ideas of
physics, neural networks are derived “naturally.” And you can learn the concepts of
deep learning through the words of physics.
In fact, the foundation of machine learning can be attributed to physical concepts. Hamiltonians that determine physical systems characterize various machine
learning structures. Statistical physics given by Hamiltonians defines machine
learning by neural networks. Furthermore, solving inverse problems in physics
through machine learning and generalization essentially provides progress and even
revolutions in physics. For these reasons, in recent years, interdisciplinary research
in machine learning and physics has been expanding dramatically.
This book is written for anyone who wants to know, learn, and apply the
relationship between deep learning/machine learning and physics. 1 All you need to
read this book is just the basic concepts in physics: energy and Hamiltonians. 2 The
concepts of statistical mechanics and the bracket notation of quantum mechanics,
which are introduced in columns, are used to explain deep learning frameworks.
This book is divided into two parts. The first part concerns understanding the
machine learning method from the perspective of physics, and the second part
1 If the reader has learnt physics and then reads a general machine learning textbook, the reader may
feel uncomfortable with how various concepts are introduced suddenly and empirically without
explanation. This book is motivated by such gaps. On the other hand, code implementation is not
covered in this book, because it is library dependent. The reader can try to implement a machine
with some favorite library.
2 It is assumed that readers learned the basics of physics: around second or third grade of
undergraduate courses in physics. We will explain everything based on Hamiltonians, but it is
not necessary to have knowledge on analytical mechanics.
vii
What is deep learning for those who want to study physics? Is it completely different
from physics? Or is it really similar?
In recent years, machine learning, including deep learning, has begun to be used
in various physics studies. Why is that? Is knowing physics useful in machine
learning? Conversely, is knowing machine learning useful in physics?
This book is devoted to answers of these questions. Starting with basic ideas of
physics, neural networks are derived “naturally.” And you can learn the concepts of
deep learning through the words of physics.
In fact, the foundation of machine learning can be attributed to physical concepts. Hamiltonians that determine physical systems characterize various machine
learning structures. Statistical physics given by Hamiltonians defines machine
learning by neural networks. Furthermore, solving inverse problems in physics
through machine learning and generalization essentially provides progress and even
revolutions in physics. For these reasons, in recent years, interdisciplinary research
in machine learning and physics has been expanding dramatically.
This book is written for anyone who wants to know, learn, and apply the
relationship between deep learning/machine learning and physics. 1 All you need to
read this book is just the basic concepts in physics: energy and Hamiltonians. 2 The
concepts of statistical mechanics and the bracket notation of quantum mechanics,
which are introduced in columns, are used to explain deep learning frameworks.
This book is divided into two parts. The first part concerns understanding the
machine learning method from the perspective of physics, and the second part
1 If the reader has learnt physics and then reads a general machine learning textbook, the reader may
feel uncomfortable with how various concepts are introduced suddenly and empirically without
explanation. This book is motivated by such gaps. On the other hand, code implementation is not
covered in this book, because it is library dependent. The reader can try to implement a machine
with some favorite library.
2 It is assumed that readers learned the basics of physics: around second or third grade of
undergraduate courses in physics. We will explain everything based on Hamiltonians, but it is
not necessary to have knowledge on analytical mechanics.
vii