I just finished reading Andrew Ng’s new book ‘Machine Learning Yearning’ and would like to recommend it to everyone interested in learning more about managing machine learning projects.
Andrew Ng is one of the world’s thought-leaders in the field of machine learning. Many of his lectures and MOOCs are freely available online and they are great resources for hands-on tips around running machine learning projects and prioritizing the next steps as a team. In his new book, the author compiles many of these nuggets of wisdom, otherwise hidden in hour-long video lectures, in a single resource.
The book includes many easily understandable explanations of otherwise quite theoretical concepts in machine learning. One figure that stood out for me is the following matrix explaining the relationship between bias, variance, and dataset mismatches, concepts usually hidden behind many layers of maths, in a very accessible manner:
The book is split into many short, easily digestible chapters and is quite short (120 pdf pages). This makes the book a great reference for every member of a machine learning team working on their next product. While most examples in the book refer to deep neural networks as the model of choice, all concepts translate very well to most other machine learning approaches
Get a free draft copy of the book here: http://www.mlyearning.org/