AI for physics

목차 (Table of Contents)

• CONTENTS
• Acknowledgments = xi
• Contributors = xiii
• List of Abbreviations = xvii
• Part I. Opening
• 1 Gathering the Team = 3
• AI and Machine Learning = 3
• A Brief History of Physics = 5
• References = 8
• 2 Teamplay = 11
• Machine Learning Physics = 11
• Impact of Physics on Machine Learning = 14
• Statistical Physics of ML = 15
• Analog Computers = 16
• Quantum Computers = 17
• Machine Learning the Physical World from Subatomic to Cosmic Scales = 19
• References = 23
• 3 The Rules of the Game = 27
• Supervised Learning = 28
• Classification versus Regression = 28
• Simple Mappings = 29
• Complex Mappings = 29
• River Deep - Mountain High = 31
• Choosing the Number of Parameters as a Balancing Act = 32
• Bias-Variance Trade-off = 33
• Kernel Methods = 33
• Decision Trees = 34
• Artificial Neural Networks = 34
• Treating Uncertainty and Prior Knowledge : Bayesian Inference = 36
• Symbolic Regression = 37
• Unsupervised Learning = 37
• Clustering and Principal Component Analysis = 38
• Autoencoders = 38
• Physics-Inspired Algorithm : Restricted Boltzmann Machine = 39
• Generative Adversarial Networks = 39
• Reinforcement Learning = 40
• What’s Next? = 40
• References = 40
• Part II. Machine-Learning the World from Subatomic to Cosmic Scales
• 4 AI for Particle Physics = 45
• The Standard Model = 46
• Open Problems = 48
• Theories beyond SM = 49
• Machine Learning Particle Physics = 49
• Cut-Based Event Selection in a Particle Physics Experiment = 50
• Particle and Event Selection with Neural Networks and Boosted Decision Trees = 50
• Machine Learning for Jet Physics = 51
• Convolutional Neural Networks for Neutrino Experiments = 54
• References = 56
• 5 AI for Molecular Physics = 59
• Speeding Up Simulations I : Machine Learning Atomistic Force Fields = 61
• Using Machine Learning to Analyze Output of Simulations = 63
• Speeding up Simulations II : Machine Learning Coarse-Grained Force Fields = 66
• References = 68
• 6 AI for Condensed Matter Physics = 71
• Using Machine Learning to Overcome Sampling Problem for Spin Glasses = 72
• Machine Learning Topological Order Transition = 75
• Machine Learning Quantum Many-Body Systems = 77
• Looking from Outside : Machine Learning Quantum Tomography = 78
• Machine Learning Based Design of New Materials and Quantum States = 78
• References = 80
• 7 AI for Cosmology = 83
• The Concordance Model of Cosmology = 83
• Machine Learning Big Data and the Global Shape of the Universe = 85
• Machine Learning New Physics versus Instrumental Effects = 87
• Machine Learning Photometric Redshift = 88
• Objects in the Mirror May Be Bluer Than They Appear = 88
• AI to the Rescue - But with the Right Architecture and Training = 90
• Machine Learning Cosmic Structure = 91
• Bubble Universes All the Way Down = 91
• Distortion Probes Gravitation : Interstellar Lensing = 92
• Fishing for Complements with the Cosmic Web = 93
• Machine Learning Gravitational Waves = 94
• Note = 98
• References = 98
• Part III. Showdown
• 8 AI for Theory of Everything = 103
• Physics and Geometry = 103
• String Theory = 104
• Extra Dimensions = 104
• Why String Theory? = 105
• Machine-Learning the Landscape = 106
• The String Landscape and Vacuum Degeneracy Problem = 107
• More on Machine-Learning the Landscape = 109
• Epilogue = 113
• References = 113
• 9 Conclusion and Outlook = 115
• References = 117
• Appendix : Table of Contents for Electronic Supplement = 119
• Index = 121