Rob Thomas and Jean-François Puget published “A Practical Guide to Machine Learning: Understand, Differentiate, and Apply“. Along with typical Machine Learning traps, it provides practical advises, e.g.: 1) “Move application development from programming to training: instead of writing new code, the application developer trains the same application with new data.” 2) “Learn continuously by monitoring the effectiveness of predictions and retraining when needed.” The guide is short but meaningful.