Machine Learning - A Comprehensive, Step-by-Step Guide to Learning and Applying Advanced Concepts and Techniques in Machine Learning: 3

© Copyright 2018 Peter Bradley- All rights reserved.

The contents of this book may not be reproduced, duplicated or transmitted without direct written permission from the author

Under no circumstances will any legal responsibility or blame be held against the publisher for any reparation, damages, or monetary loss due to the information herein, either directly or indirectly.

Legal Notice:

This book is copyright protected. This is only for personal use. You cannot amend, distribute, sell, use, quote or paraphrase any part or the content within this book without the consent of the author.

Disclaimer Notice:

Please note the information contained within this document is for educational and entertainment purposes only. Every attempt has been made to provide accurate, up to date and reliable complete information. No warranties of any kind are expressed or implied. Readers acknowledge that the author is not engaging in the rendering of legal, financial, medical or professional advice. The content of this book has been derived from various sources. Please consult a licensed professional before attempting any techniques outlined in this book.

By reading this document, the reader agrees that under no circumstances is the author responsible for any losses, direct or indirect, which are incurred as a result of the use of information contained within this document, including, but not limited to, —errors, omissions, or inaccuracies.

Table of Contents

Introduction

Chapter One: Machine-Learning versus Deep Learning

An Overview

Data Size

Interpretability

Choosing Between Deep Learning and Machine-learning

Chapter Two: Steps in Building a Machine-Learning System

Define Objective

Collect Data

Prepare Data

Select Algorithm

Train Model

Test Model

Predict

Deploy

Chapter Three: Why Use Python for Machine-Learning

Running Python

Installing on Windows

Installing on Other Systems

Advantages of Using Python

Python Libraries

Chapter Four: Supervised Algorithms Implementation

Simple Linear Regression

Steps To Build The Model

Multiple Regression

Decision Trees

K-Nearest Neighbor Algorithm

Chapter Five: Unsupervised Learning Algorithms

Clustering

Implementation of Clustering Algorithms

Chapter Six: Python Environment for Deep Learning

Installation of Keras, TensorFlow and Theano

Chapter Seven: How to Evaluate the Performance of a Deep Learning Model

Empirically Evaluate Network Configurations

Data Splitting

Manual k-Fold Cross-Validation

Chapter Eight: How to Save and Load Deep Learning Models

Save Your Neural Network Model to JSON

Save Your Neural Network Model to YAML

Chapter Nine: Reducing Dropouts in Deep Learning Models

Dropout Regularization For Neural Networks

Regularizing Dropouts in Keras

Tips For Using Dropout

Conclusion

Sources

Introduction

Thank you for purchasing the book, ‘Machine Learning - A Comprehensive, Step-by-Step Guide to Learning and Applying Advanced Concepts and Techniques in Machine Learning.’

The first two parts of the series covered the basics of machine learning, deep learning and neural networks. In the second book, readers learnt how to build a machine-learning model in Python using Sci-kit learn and some panda libraries. We also learnt how to build a neural network in Python using Keras.

In this book, you will learn to build some supervised and unsupervised machine-learning algorithms in Python using some panda libraries. Before you learn about the different algorithms, we will look at why we use Python to build machine-learning algorithms and artificial neural networks. Since we learnt how to build a neural network in the previous book, we will need to learn to evaluate that network. This book will show you different ways in which you can evaluate the performance of a neural network.

Over the course of the book, you will also gather information on saving and loading neural networks on your system. It is easier to do this since it saves time, and you can make the necessary changes to the program with ease.

I hope this book guides you on your journey to mastering machine-learning and deep learning. I wish you luck on your journey.

Chapter One: Machine-Learning versus Deep Learning

The first chapter covers the basics of artificial intelligence, and the first two books in the series provide information about machine-learning and deep learning. An algorithm to calculate the shortest path can also be an example of artificial intelligence. The two categories of artificial intelligence, namely machine-learning and deep learning are often mixed up. These two categories refer to the statistical modeling of variables in the data set to extract useful information to make informed decisions or predictions. This chapter provides some insight on why these two methods are difference. The information will also help you improve your understanding of these models.

An Overview

Machine learning is a statistical learning model where every instance in the data set is identified by a set of attributes and