AI for Physics: Machine Learning the World from Nuclear to Cosmic Scales

Description

Written in accessible language without mathematical formulas, this short book provides an overview of the wide and varied applications of artificial intelligence (AI) across the spectrum of physical sciences. Focusing in particular on AI's ability to extract patterns from data, known as machine learning (ML), the book includes a chapter on important machine learning algorithms and their respective applications in physics. It then explores the use of ML across a number of important sub-fields in more detail, ranging from particle, molecular and condensed matter physics, to astrophysics, cosmology and the theory of everything. The book covers such applications as the search for new particles and the detection of gravitational waves from the merging of black holes, and concludes by discussing what the future may hold. Cover Half Title Series Page Title Page Copyright Page Table of Contents Acknowledgments Contributors List of Abbreviations Part I Opening Chapter 1 Gathering the Team AI and Machine Learning A Brief History of Physics References Chapter 2 Teamplay Machine Learning Physics Impact of Physics on Machine Learning Statistical Physics of ML Analog Computers Quantum Computers Machine Learning the Physical World from Subatomic to Cosmic Scales References Chapter 3 The Rules of the Game Supervised Learning Classification versus Regression Simple Mappings Complex Mappings River Deep – Mountain High Choosing the Number of Parameters as a Balancing Act Bias-Variance Trade-off Kernel Methods Decision Trees Artificial Neural Networks Treating Uncertainty and Prior Knowledge: Bayesian Inference Symbolic Regression Unsupervised Learning Clustering and Principal Component Analysis Autoencoders Physics-Inspired Algorithm: Restricted Boltzmann Machine Generative Adversarial Networks Reinforcement Learning What’s Next? References Part II Machine-Learning the World from Subatomic to Cosmic Scales Chapter 4 AI for Particle Physics The Standard Model Open Problems Theories beyond SM Machine Learning Particle Physics Cut-Based Event Selection in a Particle Physics Experiment Particle and Event Selection with Neural Networks and Boosted Decision Trees Machine Learning for Jet Physics Convolutional Neural Networks for Neutrino Experiments References Chapter 5 AI for Molecular Physics Speeding Up Simulations I: Machine Learning Atomistic Force Fields Using Machine Learning to Analyze Output of Simulations Speeding up Simulations II: Machine Learning Coarse-Grained Force Fields References Chapter 6 AI for Condensed Matter Physics Using Machine Learning to Overcome Sampling Problem for Spin Glasses Machine Learning Topological Order Transition Machine Learning Quantum Many-Body Systems Looking from Outside: Machine Learning Quantum Tomography Machine Learning Based Design of New Materials and Quantum States References Chapter 7 AI for Cosmology The Concordance Model of Cosmology Machine Learning Big Data and the Global Shape of the Universe Machine Learning New Physics versus Instrumental Effects Machine Learning Photometric Redshift Objects in the Mirror May Be Bluer Than They Appear AI to the Rescue – But with the Right Architecture and Training Machine Learning Cosmic Structure Bubble Universes All the Way Down Distortion Probes Gravitation: Interstellar Lensing Fishing for Complements with the Cosmic Web Machine Learning Gravitational Waves Note References Part III Showdown Chapter 8 AI for Theory of Everything Physics and Geometry String Theory Extra Dimensions Why String Theory? Machine-Learning the Landscape The String Landscape and Vacuum Degeneracy Problem More on Machine-Learning the Landscape Epilogue References Chapter 9 Conclusion and Outlook References Appendix: Table of Contents for Electronic Supplement Index