Deep learning is a branch of machine learning, which tries to imitate the working principle of the human brain to interpret data, such as images, sounds and texts. In order to deeply understand the principles and techniques of deep learning, it is necessary to have a deep understanding of some mathematical concepts. The following are some book recommendations about deep learning mathematics:

1. Deep Learning Byiangoodflow, Yoshuabengio, Andaaroncourville: This book is a classic in the field of deep learning, and introduces the basic principles and algorithms of deep learning in detail. The book contains a large number of mathematical deductions and examples, which are suitable for readers with a certain mathematical foundation.

2. Linear algebra and its application gilbertstrand: Linear algebra is the foundation of deep learning. This book introduces the basic concepts and methods of linear algebra in detail, including vector space, matrix operation, eigenvalue and eigenvector. The book is rich in examples and clear in explanation, which is suitable for beginners.

3. Morris's probability theory and mathematical statistics. Degroot: Probability theory and statistics are commonly used mathematical tools in deep learning. This book introduces the basic concepts and methods of probability theory and statistics in detail, including probability distribution, conditional probability, random variable, expected value and variance. The book is rich in examples and clear in explanation, which is suitable for beginners.

4. Calculus) byMichaelSpivak: Calculus is a common mathematical tool in deep learning. This book introduces the basic concepts and methods of calculus in detail, including limit, derivative, integral and series. The book is rich in examples and clear in explanation, which is suitable for beginners.

5. Optimization method of learning: Optimization method is a common mathematical tool in deep learning. This book introduces the basic concepts and methods of optimization methods in detail, including gradient descent method, Newton method and quasi-Newton method. The book is rich in examples and clear in explanation, which is suitable for beginners.