Book Image

Machine Learning with Swift

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

Machine Learning with Swift

By: Jojo Moolayil, Alexander Sosnovshchenko, 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 (18 chapters)
Title Page
Packt Upsell
Contributors
Preface
Index

Inference-only libraries


With the release of iOS 11, several popular machine learning frameworks became compatible with it on the model level. You can build and train your models with these frameworks, then export them in a framework-specific format and convert them to the CoreML format for future integration with your app. Such models have fixed parameters and can be used only for inference. As Xcode generates a separate Swift class for each of those models, there is no way to replace or update them in the runtime. The main usage area for such models are different pattern-recognizing applications, like count your calories by taking a photo. At the time of writing this book (iOS 11 Beta), CoreML is compatible with the following libraries and models:

  • Caffe 1.0: Neural networks
  • Keras 1.2.2: Neural networks
  • libSVM 3.22: SVM
  • scikit-learn 0.18.1: Tree ensembles, generalized linear models, SVM, feature engineering, and pipelines
  • XGBoost 0.6: Gradient-boosted trees

All these libraries are long-standing...