Machine Learning in Mobile Applications

Course details

An excellent understanding of software development does not always transfer to a full understanding of what machine learning is or how it works. Machine learning can be used in a wide variety of scenarios within mobile development. In this course, development practice lead Kevin Ford examines these scenarios and how developers can implement machine learning into their mobile applications. After a useful primer on machine learning that’s specific to mobile development, dive into server models like Watson and Azure, as well as client models like Core ML and ML Kit. Plus, build your understanding of the offerings that are currently available.

Concepts

0. Introduction

01 - Introduction to machine learning in mobile applications
02 - What you should know to take this class
03 - Setting up your machine
04 - Using the exercise files

1. Mobile Developers Primer on Machine Learning

05 - What is machine learning
06 - Required concepts
07 - Why does this matter for my app
08 - Training a model
09 - Machine learning vs. deep learning vs. generative AI
10 - What can I do with machine learning
11 - Server-side vs. client-side ML
12 - ML frameworks

2. Server Models - IBM Watson

13 - Overview of Watson
14 - Natural Language Understanding - Setup
15 - watsonx.ai AI studio - Setup
16 - watsonx.ai AI studio - Training
17 - Deploying the model
18 - Authenticating against a deployed model
19 - Installing the Watson SDK into your mobile app
20 - Calling Watson Natural Language Understanding
21 - Returning a watsonx access token
22 - Calling a watsonx custom model
23 - Running the app
24 - Challenge - Use Natural Language Understanding features
25 - Solution - Use Natural Language Understanding features

3. Server Models - Azure

26 - Azure Machine Learning overview
27 - Language Understanding - Setup
28 - Language Understanding - Using Language Studio
29 - Language Understanding - Train, deploy, and test
30 - Custom Vision - Setup
31 - Azure Machine Learning Studio - Setup
32 - Azure Machine Learning Studio - Create a model
33 - Azure Machine Learning Studio - Deploy and test a model
34 - Install the SDK in a mobile app
35 - Tie to Language Understanding
36 - Tie to Custom Vision
37 - Prepare Android and iOS apps to consume non-SSL endpoints
38 - Tie to the Azure Machine Learning Studio model
39 - Running the app
40 - Challenge - Create a custom Language Understanding model
41 - Solution - Create a custom Language Understanding model

4. Client Models - Core ML

42 - Core ML overview
43 - Core ML - Create a natural language model
44 - Core ML - Create a visual recognition model
45 - Core ML - Create a regression model
46 - Client tied to a natural language model
47 - Client tied to a visual recognition model
48 - Client tied to a regression model
49 - Running the app
50 - Challenge - Create a custom model
51 - Solution - Create a custom model

5. Client Models - ML Kit

52 - Introduction to ML Kit
53 - Selecting a model
54 - Adding the SDK to a mobile app
55 - Calling the model
56 - Running the app
57 - Challenge - Implement the image labeling model
58 - Solution - Implement the image labeling model

6. Understanding the Offerings

59 - Different philosophies of the vendors
60 - Why use client-side vs. server-side models
61 - When to use one or another of these solutions

Conclusion

62 - Where to go from here