Mathematical Theory of Deep Learning
Buch in deiner Nähe kaufen
Beschreibung
This open access book offers a comprehensive introduction to a wide variety of topics in the mathematical theory of deep learning. These include questions pertaining to the prowess of deep neural networks, the surprising effectiveness of current learning algorithms, and the puzzling capability of huge neural networks to make accurate predictions on unseen data. The text focuses on rigorous but accessible results, and provides deep insights into the reasons why this field has been so successful. The book proves useful for mathematicians with a working knowledge of probability theory, linear algebra, and analysis.
This open access book offers a comprehensive introduction to a wide variety of topics in the mathematical theory of deep learning. These include questions pertaining to the prowess of deep neural networks, the surprising effectiveness of current learning algorithms, and the puzzling capability of huge neural networks to make accurate predictions on unseen data. The text focuses on rigorous but accessible results, and provides deep insights into the reasons why this field has been so successful. The book proves useful for mathematicians with a working knowledge of probability theory, linear algebra, and analysis.
This book is open access, which means that you have free and unlimited access Uniquely blends theoretical math and deep learning, offering readers a comprehensive understanding of the subjects Presents deep learning via provable statements and explanations, perfect for mathematicians Focuses on the role of depth in deep learning and explores advanced topics
Autor*in
Philipp Petersen
Themen in »Mathematical Theory of Deep Learning«
Open Access deep learning neural networks machine learning training of neural networks neural network approximation theory generalization for neural networks optimization for neural networks loss landscape analysis mathematics of deep learning theory of deep learning