Part I Foundations

Chapter 1 Machine Learning

Deep learning belongs historically to the larger field of statistical machine learning, as it fundamentally concerns methods able to learn representations from data. The techniques involved come originally from artificial neural networks, and the “deep” qualifier highlights that models are long compositions of mappings, now known to achieve greater performance.

The modularity of deep models, their versatility, and scaling qualities, have resulted in a plethora of specific mathematical methods and software development tools that have established deep learning as a separate and vast technical field.