Machine learning for physicists : a hands-on approach / Sadegh Raeisi, Sedighe Raeisi.

Format:

Book

Author/Creator:

Raeisi, Sadegh, author.

Raeisi, Sedighe, author.

Contributor:

Institute of Physics (Great Britain), publisher.

Series:

IOP (Series). Release 23.

IOP ebooks. 2023 collection.

[IOP release $release]

IOP ebooks. [2023 collection]

Language:

English

Subjects (All):

Physics--Data processing.

Physics.

Machine learning.

Physical Description:

1 online resource (various pagings) : illustrations (some color).

Place of Publication:

Bristol [England] (Temple Circus, Temple Way, Bristol BS1 6HG, UK) : IOP Publishing, [2023]

System Details:

Mode of access: World Wide Web.

System requirements: Adobe Acrobat Reader, EPUB reader, or Kindle reader.

Biography/History:

Sadegh Raeisi has a background in quantum computing and quantum information science. He completed his MSc at the University of Calgary and his PhD at the Institute for Quantum Computing at the University of Waterloo, as well as a Postdoc at the Max Planck Institute for the Science of Light in Erlangen. He then moved back to his home country and has held a faculty position since 2017. With about 18 years of research experience within the field of quantum computing, Sadegh is probably most recognized for his pioneering works on macroscopic quantumness and algorithmic cooling, including finding the cooling limit of heat-bath algorithmic cooling (HBAC) techniques which was an open problem for a decade, and for inventing the Blind HBAC technique, which is the optimal and practical HBAC technique. Sedighe Raeisi has a background in high-energy physics, nonlinear dynamics and chaotic systems. She holds a PhD from Ferdowsi University of Mashhad where she also worked for two years as a lecturer after graduation. Her areas of expertise include machine learning and deep learning with special focus on natural language processing (NLP), machine vision, graph neural networks and time series forecasting. She is currently working as a data scientist in the research and development division of Iran's largest telecommunications company.

Summary:

This book presents machine learning (ML) concepts with a hands-on approach for physicists. The goal is to both educate and enable a larger part of the community with these skills. This will lead to wider applications of modern ML techniques in physics. Accessible to physical science students, the book assumes a familiarity with statistical physics but little in the way of specialized computer science background. All chapters start with a simple introduction to the basics and the foundations, followed by some examples, and then proceeds to provide concrete examples with associated codes from a GitHub repository. Many of the code examples provided can be used as is or with suitable modification by the students for their own applications.

Contents:

1. Preliminaries

1.1. Python

1.2. GitHub library

1.3. Datasets

2. Introduction

2.1. What is machine learning?

2.2. Applications of machine learning

2.3. Different types of machine learning

2.4. Structure of the book

part I. Supervised learning. 3. Supervised learning

3.1. Definitions, notations, and problem statement

3.2. Ingredients of supervised learning

3.3. Model evaluation and model selection

3.4. Summary

3.5. Questions

4. Neural networks

4.1. Introduction to neural networks

4.2. Training neural networks

4.3. Libraries for working with neural networks

4.4. Summary

5. Special neural networks

5.1. Convolutional neural network (CNN)

5.2. Time-series and recurrent neural networks (RNNs)

5.3. Graph neural network

5.4. Summary

part II. Unsupervised learning. 6. Unsupervised learning

6.1. Clustering

6.2. Anomaly detection

6.3. Dimensionality reduction

6.4. Summary

7. Generative models

7.1. Maximum likelihood estimation

7.2. Restricted Boltzmann machines

7.3. Generative adversarial networks (GAN)

7.4. Summary.

Notes:

"Version: 20231101"--Title page verso.

Includes bibliographical references.

Title from PDF title page (viewed on December 1, 2023).

Other Format:

Print version:

ISBN:

9780750349574

9780750349567

OCLC:

1412322926

Access Restriction:

Restricted for use by site license.