(This blog post represents my personal opinion, and should not be interpreted as any official statements from my employer NVIDIA.)
If you read the bibliography at the end of Learning Deep Learning you will find that the book is based on a large number of publications. I have done my best to give credit to all authors of works upon which this book is based. A careful reader of the book might notice that four different books particularly inspired me. This is what I liked about them:
- Neural Networks and Deep Learning by Nielsen – This is a nice introduction to the topic of neural network. In particular, I liked the programming example implementing a network for handwritten digit recognition from scratch in Python.
- Deep Learning From Basics to Practice by Glassner – This two-volume book describes both traditional machine learning and deep learning in a very accessible manner. Glassner describes the concepts in an intuitive way with a large number of figures and no mathematics. In addition to explaining the concepts he also provides programming examples to get started with both scikit-learn and TensorFlow. Glassner recently released Deep Learning – A Visual Approach, which is a reworked version of the original book.
- Deep Learning with Python by Cholet – This is a great book if you want to get started with building deep neural networks with TensorFlow.
- Deep Learning by Goodfellow, Bengio, and Courville – This book approaches the topic from a mathematical and theoretical perspective and includes an introduction to traditional machine learning. However, it is a heavy text to get through so I don’t recommend it unless you already have advanced skills in mathematics and statistics.