Provides an overview for scientists of how machine learning can help to discover physical concepts
Introduces a general framework that can help the reader to extract relevant parameters from experimental data
The content of the book is easily accessible even to scientists without background knowledge in machine learning
Raban Iten studied Physics and Mathematics at ETH Zürich, followed by a Ph.D. in quantum computation. During his Ph.D., he worked on using machine learning to discover physical concepts from experimental data of classical and quantum systems. This work was widely covered in the media and pointed out as a research highlight of 2019 by Nature Reviews Physics. Furthermore, he developed algorithms for quantum compilers and contributed to various open-source libraries for quantum computing.
Will research soon be done by artificial intelligence, thereby making human researchers superfluous? This book explains modern approaches to discovering physical concepts with machine learning and elucidates their strengths and limitations. The automation of the creation of experimental setups and physical models, as well as model testing are discussed. The focus of the book is the automation of an important step of the model creation, namely finding a minimal number of natural parameters that contain sufficient information to make predictions about the considered system. The basic idea of this approach is to employ a deep learning architecture, SciNet, to model a simplified version of a physicist's reasoning process. SciNet finds the relevant physical parameters, like the mass of a particle, from experimental data and makes predictions based on the parameters found. The author demonstrates how to extract conceptual information from such parameters, e.g., Copernicus' conclusion that the solar system is heliocentric.
Introduction.- Machine Learning Background.- Overview of Using Machine Learning for Physical Discoveries.- Theory: Formalizing the Process of Human Model Building.- Methods: Using Neural Networks to Find Simple Representations.- Applications: Physical Toy Examples.- Open Questions and Future Prospects.
Will research soon be done by artificial intelligence, thereby making human researchers superfluous? This book explains modern approaches to discovering physical concepts with machine learning and elucidates their strengths and limitations. The automation of the creation of experimental setups and physical models, as well as model testing are discussed. The focus of the book is the automation of an important step of the model creation, namely finding a minimal number of natural parameters that contain sufficient information to make predictions about the considered system. The basic idea of this approach is to employ a deep learning architecture, SciNet, to model a simplified version of a physicist's reasoning process. SciNet finds the relevant physical parameters, like the mass of a particle, from experimental data and makes predictions based on the parameters found. The author demonstrates how to extract conceptual information from such parameters, e.g., Copernicus' conclusion that the solar system is heliocentric.
Will research soon be done by artificial intelligence, thereby making human researchers superfluous? This book explains modern approaches to discovering physical concepts with machine learning and elucidates their strengths and limitations. The automation of the creation of experimental setups and physical models, as well as model testing are discussed. The focus of the book is the automation of an important step of the model creation, namely finding a minimal number of natural parameters that contain sufficient information to make predictions about the considered system. The basic idea of this approach is to employ a deep learning architecture, SciNet, to model a simplified version of a physicist's reasoning process. SciNet finds the relevant physical parameters, like the mass of a particle, from experimental data and makes predictions based on the parameters found. The author demonstrates how to extract conceptual information from such parameters, e.g., Copernicus' conclusion that the solar system is heliocentric.
Raban Iten studied Physics and Mathematics at ETH Zürich, followed by a Ph.D. in quantum computation. During his Ph.D., he worked on using machine learning to discover physical concepts from experimental data of classical and quantum systems. This work was widely covered in the media and pointed out as a research highlight of 2019 by Nature Reviews Physics. Furthermore, he developed algorithms for quantum compilers and contributed to various open-source libraries for quantum computing.
Inhaltsverzeichnis
Introduction.- Machine Learning Background.- Overview of Using Machine Learning for Physical Discoveries.- Theory: Formalizing the Process of Human Model Building.- Methods: Using Neural Networks to Find Simple Representations.- Applications: Physical Toy Examples.- Open Questions and Future Prospects.
Klappentext
Will research soon be done by artificial intelligence, thereby making human researchers superfluous? This book explains modern approaches to discovering physical concepts with machine learning and elucidates their strengths and limitations. The automation of the creation of experimental setups and physical models, as well as model testing are discussed. The focus of the book is the automation of an important step of the model creation, namely finding a minimal number of natural parameters that contain sufficient information to make predictions about the considered system. The basic idea of this approach is to employ a deep learning architecture, SciNet, to model a simplified version of a physicist's reasoning process. SciNet finds the relevant physical parameters, like the mass of a particle, from experimental data and makes predictions based on the parameters found. The author demonstrates how to extract conceptual information from such parameters, e.g., Copernicus' conclusion that the solar system is heliocentric.
Provides an overview for scientists of how machine learning can help to discover physical concepts
Introduces a general framework that can help the reader to extract relevant parameters from experimental data
The content of the book is easily accessible even to scientists without background knowledge in machine learning
