Deep Learning in Science

Erscheinungsjahr 2021
ISBN: 978-1-108-84535-9
Verlag: Cambridge University Press

Buch, Englisch, 450 Seiten, Format (B × H): 174 mm x 250 mm, Gewicht: 910 g

This is the first rigorous, self-contained treatment of the theory of deep learning. Starting with the foundations of the theory and building it up, this is essential reading for any scientists, instructors, and students interested in artificial intelligence and deep learning. It provides guidance on how to think about scientific questions, and leads readers through the history of the field and its fundamental connections to neuroscience. The author discusses many applications to beautiful problems in the natural sciences, in physics, chemistry, and biomedicine. Examples include the search for exotic particles and dark matter in experimental physics, the prediction of molecular properties and reaction outcomes in chemistry, and the prediction of protein structures and the diagnostic analysis of biomedical images in the natural sciences. The text is accompanied by a full set of exercises at different difficulty levels and encourages out-of-the-box thinking.

Autoren/Hrsg.

Baldi, Pierre

Fachgebiete

• Geowissenschaften Geographie | Raumplanung Geodäsie, Kartographie, GIS, Fernerkundung
• Interdisziplinäres Wissenschaften Wissenschaften: Forschung und Information Datenanalyse, Datenverarbeitung
• Geowissenschaften Geologie Geodäsie, Kartographie, Fernerkundung
• Mathematik | Informatik EDV | Informatik Informatik Mathematik für Informatiker
• Mathematik | Informatik EDV | Informatik Daten / Datenbanken Automatische Datenerfassung, Datenanalyse
• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz Maschinelles Lernen
• Sozialwissenschaften Medien- und Kommunikationswissenschaften Kommunikationswissenschaften
• Interdisziplinäres Wissenschaften Wissenschaften Interdisziplinär Naturwissenschaften, Technik, Medizin

Inhaltsverzeichnis

1. Introduction; 2. Basic Concepts; 3. Shallow Networks and Shallow Learning; 4. Two-Layer Networks and Universal Approximation; 5. Autoencoders; 6. Deep Networks and Backpropagation; 7. The Local Learning Principle; 8. The Deep Learning Channel; 9. Recurrent Networks; 10. Recursive Networks; 11. Applications in Physics; 12. Applications in Chemistry; 13. Applications in Biology and Medicine; 14. Conclusion; Appendix A. Reinforcement Learning and Deep Reinforcement Learning; Appendix B. Hints and Remarks for Selected Exercises; References; Index.

Über Autor(innen)

Baldi, Pierre
Pierre Baldi is Distinguished Professor of Computer Science at University of California, Irvine. His main research interest is understanding intelligence in brains and machines. He has made seminal contributions to the theory of deep learning and its applications to the natural sciences, and has written four other books.