Book Image

Machine Learning with Swift

By : Alexander Sosnovshchenko, Jojo Moolayil, Oleksandr Baiev
Book Image

Machine Learning with Swift

By: Alexander Sosnovshchenko, Jojo Moolayil, Oleksandr Baiev

Overview of this book

Machine learning as a field promises to bring increased intelligence to the software by helping us learn and analyse information efficiently and discover certain patterns that humans cannot. This book will be your guide as you embark on an exciting journey in machine learning using the popular Swift language. We’ll start with machine learning basics in the first part of the book to develop a lasting intuition about fundamental machine learning concepts. We explore various supervised and unsupervised statistical learning techniques and how to implement them in Swift, while the third section walks you through deep learning techniques with the help of typical real-world cases. In the last section, we will dive into some hard core topics such as model compression, GPU acceleration and provide some recommendations to avoid common mistakes during machine learning application development. By the end of the book, you'll be able to develop intelligent applications written in Swift that can learn for themselves.
Table of Contents (14 chapters)

Getting Started with Machine Learning

We live in exciting times. Artificial intelligence (AI) and Machine Learning  (ML) went from obscure mathematical and science fiction topics to become a part of mass culture. Google, Facebook, Microsoft, and others competed to become the first to give the world general AI. In November 2015, Google open sourced its ML framework with TensorFlow, which is suitable for running on supercomputers as well as smartphones, and since then has won a broad community. Shortly afterwards, other big companies followed the example. The best iOS app of 2016 (Apple Choice), viral photo editor Prisma owes its success entirely to a particular kind of ML algorithm: convolutional neural network (CNN). These systems were invented back in the nineties but became popular only in the noughties. Mobile devices only gained enough computational power to run them in 2014/2015. In fact, artificial neural networks became so important for practical applications that in iOS 10 Apple added native support for them in the metal and accelerate frameworks. Apple also opened Siri to third-party developers and introduced GameplayKit, a framework to add AI capabilities to your computer games. In iOS 11, Apple introduced Core ML, a framework for running pre-trained models on vendors' devices, and Vision framework for common computer vision tasks.

The best time to start learning about ML was 10 years ago. The next best time is right now.

In this chapter, we will cover the following topics:

  • Understanding what AI and ML is
  • Fundamental concepts of ML : model, dataset, and learning
  • Types of ML tasks
  • ML project life cycle
  • General purpose ML versus mobile ML