Machine Learning for Mobile is for you if you are a mobile developer or machine learning user who aspires to exploit machine learning and use it on mobiles and smart devices. Basic knowledge of machine learning and entry-level experience with mobile application development is preferred.

Chapter 1, Introduction to Machine Learning on Mobile, explains what machine learning is and why we should use it on mobile devices. It introduces different approaches to machine learning and their pro and cons.

Chapter 2, Supervised and Unsupervised Learning Algorithms, covers supervised and unsupervised approaches of machine learning algorithms. We will also learn about different algorithms, such as Naive Bayes, decision trees, SVM, clustering, associated mapping, and many more. 

Chapter 3, Random Forest on iOS, covers random forests and decision trees in depth and explains how to apply them to solve machine learning problems. We will also create an application using a decision tree to diagnose breast cancer.

Chapter 4, TensorFlow Mobile in Android, introduces TensorFlow for mobile. We will also learn about the architecture of a mobile machine learning application and write an application using TensorFlow in Android. 

Chapter 5, Regression Using Core ML in iOS, explores regression and Core ML and shows how to apply it to solve a machine learning problem. We will be creating an application using scikit-learn to predict house prices. 

Chapter 6, ML Kit SDK, explores ML Kit and its benefits. We will be creating some image labeling applications using ML Kit and device and cloud APIs. 

Chapter 7, Spam Message Detection in iOS - Core ML, introduces natural language processing and the SVM algorithm. We will solve a problem of bulk SMS, that is, whether messages are spam or not. 

Chapter 8, Fritz, introduces the Fritz mobile machine learning platform. We will create an application using Fritz and Core ML in iOS. We will also see how Fritz can be used with the sample dataset we create earlier in the book. 

Chapter 9, Neural Networks on Mobile, covers the concepts of neural networks, Keras, and their applications in the field of mobile machine learning. We will be creating an application to recognize handwritten digits and also the TensorFlow image recognition model.

Chapter 10, Mobile Application Using Google Cloud Vision, introduces the Google Cloud Vision label-detection technique in an Android application to determine what is in pictures taken by a camera.

Chapter 11, Future of ML on Mobile Applications, covers the key features of mobile applications and the opportunities they provide for stakeholders.

Appendix, Question and Answers, contains questions that may be on your mind and tries to provide answers to those questions.

Readers need to have prior knowledge of machine learning, Android Studio, and Xcode.

# importing required packages
import numpy as np
import pandas as pd

# Reading in and parsing data
raw_data = open('SMSSpamCollection.txt', 'r')
sms_data = []
for line in raw_data:
    split_line = line.split("\t")
    sms_data.append(split_line)

pip install scikit-learn 
pip install numpy
pip install coremltools
pip install pandas

Feedback from our readers is always welcome.

General feedback: If you have questions about any aspect of this book, mention the book title in the subject of your message and email us at [email protected].

Errata: Although we have taken every care to ensure the accuracy of our content, mistakes do happen. If you have found a mistake in this book, we would be grateful if you would report this to us. Please visit www.packt.com/submit-errata, selecting your book, clicking on the Errata Submission Form link, and entering the details.

Piracy: If you come across any illegal copies of our works in any form on the Internet, we would be grateful if you would provide us with the location address or website name. Please contact us at [email protected] with a link to the material.

If you are interested in becoming an author: If there is a topic that you have expertise in and you are interested in either writing or contributing to a book, please visit authors.packtpub.com.