Summary of DL

ML is the ingredient to make our tiny devices capable of making intelligent decisions. These software algorithms heavily rely on the right data to learn patterns or actions based on experience. As we commonly say, data is everything for ML because it is what makes or breaks an application.

This book will refer to DL as a specific class of ML that can perform complex classification tasks directly on raw images, text, or sound. These algorithms have state-of-the-art accuracy and could also be better than humans in some classification problems. This technology makes voice-controlled virtual assistants, facial recognition systems, and autonomous driving possible, just to name a few.

A complete discussion of DL architectures and algorithms is beyond the scope of this book. However, this section will summarize some of its essential points that are relevant to understand the following chapters.

Deep neural networks

A deep neural network consists of several stacked...