Quantum Chemistry in the Age of Machine Learning covers this exciting field in detail, ranging from basic concepts to comprehensive methodologies. Such an approach helps readers get a quick overview of existing techniques, providing users with an opportunity to learn the intricacies and inner working of the state-of-the-art methods. The book describes underlying concepts of supervised and unsupervised learning applied to solve quantum chemical problems, covering the broad field of special- and general-purpose machine learning potentials, active learning, learning of various quantum chemical properties, ?-learning, improving the Hamiltonian, learning the wavefunction, and analysis of Big Data. Drawing on the experience of an expert team of contributors, this book is a valuable guide to this exciting area for both aspiring beginners and specialists in the field. Compiles advances of machine learning in quantum chemistry across different areas into a single resource Provides insights into the underlying concepts of machine learning techniques that are relevant to quantum chemistry Describes, in detail, the current state-of-the-art machine learning-based methods in quantum chemistry INDICE: Part 1: Introduction 1. Very brief introduction to quantum chemistry 2. Density functional theory 3. Semiempirical methods 4. Basics of molecular dynamics 5. From small molecules to materials science 6. Machine learning: An Overview 7. Supervised learning: Neural networks 8. Supervised learning: Kernel methods 9. Bayesian inference 10. Active learning 11. Unsupervised learning Part 2: Machine learning potentials 12. Potentials based on linear models 13. Dynamics with neural-network-based potentials 14. Dynamics with Gaussian process regression potentials 15. Dynamics with kernel ridge regression potentials 16. Excited-state dynamics 17. Vibrational spectra with machine learning 18. Finding critical points on potential energy surface: Geometry optimizations and transition state search Part 3: Machine learning of quantum chemical properties 19. Learning of electron densities 20. Learning of dipole moments 21. Learning of excited-state properties 22. Learning of other properties Part 4: Machine learning-improved quantum chemical methods 23. Machine learning for accelerating and improving ab initio wavefunction-based methods 24. Redesigning density functional theory with machine learning 25. Improved semiempirical Hamiltonians with machine learning 26. ?-learning and beyond 27. Machine learning wavefunction Part 5: Analysis of Big Data 28. Analysis of dynamics trajectories 29. Insights for rational materials design
- ISBN: 978-0-323-90049-2
- Editorial: Elsevier
- Encuadernacion: Rústica
- Páginas: 560
- Fecha Publicación: 01/09/2022
- Nº Volúmenes: 1
- Idioma: Inglés