Machine Learning: A Physicist Perspective

✍ Scribed by Nelson Bolivar

• Publisher: Arcler Press
• Year: 2023
• Tongue: English
• Leaves: 268
• Category: Library

✦ Synopsis

Deep-learning and machine-learning have gained a significant importance in the last few years. New inventions and discoveries are taking place every day to exploit the concepts of machine-learning technique. The aim of this book is to present the fundamentals of machine-learning with an emphasis on deep-learning, neural networks and physical aspects of machine learning. Design of materials and molecules with desired features is an essential prerequisite for progressing technology in our contemporary societies. This necessitates both the capability to compute precise microscopic characteristics, such as forces, energies and efficient selection of potential energy faces, to attain corresponding macroscopic features. Tools required to achieve the above mentioned goals can be extracted from quantum mechanics, statistical mechanics, and classical physics, respectively. To overcome the challenge of technology integration, significant efforts are being made to speed up quantum physical simulations with the help of machine learning. This evolving interdisciplinary community consists of material scientists, chemists, physicists, computer scientists and mathematicians, coming together to contribute to the exciting field of machine learning and artificial intelligence. This book can be used as a reference material for acquiring fundamentals of machine learning from a physicist’s perspective. Moreover, people from all backgrounds can benefit from this introductory book on Machine Learning.

✦ Table of Contents

Cover
Title Page
Copyright
ABOUT THE AUTHOR
TABLE OF CONTENTS
List of Figures
List of Tables
List of Abbreviations
Preface
Chapter 1 Fundamentals of Machine Learning
1.1. Introduction
1.2. Machine Learning: A Brief History
1.3. Terminology
1.4. Machine Learning Process
1.5. Background Theory
1.6. Machine Learning Approaches
1.7. Machine Learning Methods
1.8. Machine Learning Algorithms
1.9. Programming Languages
1.10. Human Biases
References
Chapter 2 Physical Aspects of Machine Learning in Data Science
2.1. Introduction
2.2. Theory-Guided Data Science
2.3. Weaving Motifs
2.4. Significance of TGDS
2.5. Sharing and Reusing Knowledge with Data Science
References
Chapter 3 Statistical Physics and Machine Learning
3.1. Introduction
3.2. Background and Importance
3.3. Learning as a Thermodynamic Relaxation Process and Stochastic Gradient Langevin Dynamics
3.4. Chemotaxis In Enzyme Cascades
3.5. Acquire Nanoscale Information Through Microscale Measurements Utilizing Motility Assays
3.6. Statistical Learning
3.7. Non-Equilibrium Statistical Physics
3.8. Primary Differential Geometry
3.9. Bayesian Machine Learning and Connections to Statistical Physics
3.10. Statistical Physics of Learning in Dynamic Procedures
3.11. Earlier Work
3.12. Learning as a Quenched Thermodynamic Relaxation
References
Chapter 4 Particle Physics and Cosmology
4.1. Introduction
4.2. The Simulation’s Role
4.3. Regression and Classification in Particle Physics
4.4. Regression and Classification in Cosmology
4.5. Probability-Free Inference and Inverse Problems
4.6. Generative Models
4.7. Outlook and Challenges
References
Chapter 5 Machine Learning in Artificial Intelligence
5.1. Introduction
5.2. Related Work
5.3. A Framework for Understanding the Role of Machine Learning in Artificial Intelligence
References
Chapter 6 Materials Discovery and Design Using Machine Learning
6.1. Introduction
6.2. Machine Learning Methods Description in Materials Science
6.3. The Machine Learning Applications Used in Material Property Prediction
6.4. The Use of Machine Learning Applications in the Discovery of New Materials
6.5. The Machine Learning Applications Used for Various Other Purposes
6.6. Countermeasures for and Analysis of Common Problems
References
Chapter 7 Machine Learning and Quantum Physics
7.1. Introduction
7.2. Uncovering Phases of Matter
7.3. Neural-Network Representation
7.4. Entanglement In Neural-Network Stzates
7.5. Quantum Many-Body Problems
7.6. Quantum-Enhanced Machine Learning
7.7. Future Partnership
References
Chapter 8 Modern Applications of Machine Learning
8.1. Introduction
8.2. Applications
8.3. Learning From Biological Sequences
8.4. Learning From Email Data
8.5. Focused Crawling Using Reinforcement Learning
References
Index
Back Cover