Machine Learning fundamentals that every iOS developer needs to know: 0/5 Introduction

Machine Learning fundamentals that every iOS developer needs to know series

Sometimes ML is perceived as a super complicated topic, requiring deep knowledge of various algorithms and math. While it is true on the academic level (to understand scientific papers one might need such knowledge), it doesn’t always have to be complicated on the practical level. Some problems might be much easier to solve using ML-powered technology than simply coding. iOS developer’s goal is to create intelligent applications, not improve the performance of the state of the art algorithms (leave this task for scientists working at Universities across the world or smart geniuses at Apple, Google, etc.). Such a goal sometimes can be achieved quite easily.

This is an introduction of the Machine Learning fundamentals that every iOS developer needs to know series which consists of 5 articles. Within these articles, readers will be introduced to different ways of leveraging the power of Machine Learning models in iOS app development.

• 1/5 iOS Machine Learning Architecture & Tools

  The series starts with an introduction to a high-level architecture of how Machine Learning works in iOS and helpful tools.

• 2/5 Native domain-specific Machine Learning frameworks for iOS developers

  The content of the second article will dive deeper and introduce Native Apple provided domain-specific ML frameworks that help to build intelligent iOS applications.

• 3/5 How to use a custom Core ML model in the iOS App

  In the third article of the series, readers will learn where to find and how to use Core ML models with Swift in iOS applications.

• 4/5 Training Machine Learning models for the iOS App with Create ML and Turi Create

  The fourth article presents tools for creating and training the unique Machine Learning models for the iOS project yourself.

• 5/5 How to run any Machine Learning model in the iOS App

  The Series wraps up by introducing the coremltools Python package - a tool for converting models from popular third-party training libraries such as TensorFlow and PyTorch to the Core ML format. This tool is also a must for creating models that can be updated on-device.

I hope you’ll enjoy the series of articles and learn something new that will boost the intelligence of the app you’re working on. Don’t hesitate to start a discussion in the comments or contact me directly - I’ll do my best to answer. Stay tuned!