Chapter 6
Unsupervised Deep Learning
Abstract In this chapter, at the end of Part I, we will explain Boltzmann machines
and Generative adversarial networks (GANs). Both models are not the “find an
answer” network given in Chap. 3, but rather the network itself giving the probability
distribution of the input. Boltzmann machines have historically been the cornerstone
of neural networks and are given by the Hamiltonian statistical mechanics of multiparticle spin systems. It is an important bridge between machine learning and
physics. Generative adversarial networks are also one of the important topics in
deep learning in recent years, and we try to provide an explanation of it from a
physical point of view.
Chapters 2 and 3 described machine learning when a data set consisting of an input
and a training label is given. In this chapter, we change the subject and explain the
method of machine learning when no training label is given: the case of a generative
model. 1
6.1 Unsupervised Learning
What is unsupervised learning? It is a machine learning scheme that uses data that
has only “input data” and no “answer signal” for it:
{x[i]} i=1,2,...,# .
(6.1)
1 In addition to generative models, tasks such as clustering and principal component analysis are
included in unsupervised learning. It should be noted here that in the sense that data is provided in
advance, it is different from schemes such as reinforcement learning where data is not provided.
Reinforcement learning is a very important machine learning technique that is not discussed in this
book. Instead, here we provide some references. First, the standard textbook is Ref. [76] written
by Sutton et al. This also describes the historical background.
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2021
A. Tanaka et al., Deep Learning and Physics, Mathematical Physics Studies,
https://doi.org/10.1007/978-981-33-6108-9_6
103
Unsupervised Deep Learning
Abstract In this chapter, at the end of Part I, we will explain Boltzmann machines
and Generative adversarial networks (GANs). Both models are not the “find an
answer” network given in Chap. 3, but rather the network itself giving the probability
distribution of the input. Boltzmann machines have historically been the cornerstone
of neural networks and are given by the Hamiltonian statistical mechanics of multiparticle spin systems. It is an important bridge between machine learning and
physics. Generative adversarial networks are also one of the important topics in
deep learning in recent years, and we try to provide an explanation of it from a
physical point of view.
Chapters 2 and 3 described machine learning when a data set consisting of an input
and a training label is given. In this chapter, we change the subject and explain the
method of machine learning when no training label is given: the case of a generative
model. 1
6.1 Unsupervised Learning
What is unsupervised learning? It is a machine learning scheme that uses data that
has only “input data” and no “answer signal” for it:
{x[i]} i=1,2,...,# .
(6.1)
1 In addition to generative models, tasks such as clustering and principal component analysis are
included in unsupervised learning. It should be noted here that in the sense that data is provided in
advance, it is different from schemes such as reinforcement learning where data is not provided.
Reinforcement learning is a very important machine learning technique that is not discussed in this
book. Instead, here we provide some references. First, the standard textbook is Ref. [76] written
by Sutton et al. This also describes the historical background.
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2021
A. Tanaka et al., Deep Learning and Physics, Mathematical Physics Studies,
https://doi.org/10.1007/978-981-33-6108-9_6
103