1.4 Machine Learning and Physics
11
Table 1.1 Terms and notations used in machine learning related fields and their counterparts in
physics
Machine learning
Physics
Expection value E θ [•]
Expection value •• J
Training parameters W, θ
Coupling constant (external field) J
Energy function E
Hamiltonian H
2. Finding the link between physics problems and machine learning methods
In this book, the first half is “Introduction to Machine Learning/Deep Learning
from the Perspective of Physics”, and the second half is “Application to Physics”.
Although there are many topics which are not introduced in this book, we have tried
to include references as much as possible, so readers who want to know more about
them should consult the literature or search by keywords.
In addition, the final chapter of this book describes the background of the
writing, the motivation for the research, and a message for those who are studying
machine learning, from three different perspectives of the authors. As the readers
can find there, the authors have different interconnecting opinions, and in what sense
machine learning and physics are still related is a mystery that researchers do not
completely agree with. In other words, this also means “an unexplored land where
something may exist.” With the readers who study machine learning from now, let
us step into this mysterious land, through this book.
11
Table 1.1 Terms and notations used in machine learning related fields and their counterparts in
physics
Machine learning
Physics
Expection value E θ [•]
Expection value •• J
Training parameters W, θ
Coupling constant (external field) J
Energy function E
Hamiltonian H
2. Finding the link between physics problems and machine learning methods
In this book, the first half is “Introduction to Machine Learning/Deep Learning
from the Perspective of Physics”, and the second half is “Application to Physics”.
Although there are many topics which are not introduced in this book, we have tried
to include references as much as possible, so readers who want to know more about
them should consult the literature or search by keywords.
In addition, the final chapter of this book describes the background of the
writing, the motivation for the research, and a message for those who are studying
machine learning, from three different perspectives of the authors. As the readers
can find there, the authors have different interconnecting opinions, and in what sense
machine learning and physics are still related is a mystery that researchers do not
completely agree with. In other words, this also means “an unexplored land where
something may exist.” With the readers who study machine learning from now, let
us step into this mysterious land, through this book.