The reviewer found the book 'Deep Learning' by Ian Goodfellow, Yoshua Bengio, and Aaron Courville to be a comprehensive resource for understanding deep learning concepts. They appreciated the thorough explanations of applied mathematics and machine learning basics, as well as the detailed discussions on deep learning theories and practices. The reviewer recommends the book for both beginners and experienced practitioners in the field.
The reviewer has been exploring deep learning topics from various resources but found inconsistencies in their knowledge. They decided to thoroughly read 'Deep Learning' by Ian Goodfellow, Yoshua Bengio, and Aaron Courville to gain a solid understanding of the subject. The book is divided into three parts: applied mathematics and machine learning basics, deep learning theories and practices, and deep learning research. The reviewer found the first part, which covers the basics, to be particularly valuable, as it provides a solid foundation for understanding more advanced topics. They appreciated the detailed explanations of linear algebra, probability, and information theory, as well as the discussions on numerical computations and optimization problems. The reviewer also found the chapter on machine learning basics to be informative and well-explained, providing a unique perspective on hyperparameters, cost functions, and solution algorithms. Overall, the reviewer recommends the book for anyone looking to deepen their understanding of deep learning, whether they are beginners or experienced practitioners.
Quick quotes
This part should be a good education for you.
Therefore my suggestion will be to read the first part of the book fast but thoroughly regardless of your maths/ml basics standpoint.
This chapter is specially recommended for people not experienced in machine learning previous to this book; and also is a good read for people who has begun in machine learning for just several years.