Hands-On Machine Learning with IBM Watson

图书信息

作者	James D. Miller
出版社	Packt Publishing
ISBN	9781789616279
出版时间	2019-03-29
字数	20.4万
分类	进口书,外文原版书,电脑,网络

读书简介

Learn how to build complete machine learning systems with IBM Cloud and Watson Machine learning services Key Features * Implement data science and machine learning techniques to draw insights from real-world data * Understand what IBM Cloud platform can help you to implement cognitive insights within applications * Understand the role of data representation and feature extraction in any machine learning system Book Description IBM Cloud is a collection of cloud computing services for data analytics using machine learning and artificial intelligence (AI). This book is a complete guide to help you become well versed with machine learning on the IBM Cloud using Python. Hands-On Machine Learning with IBM Watson starts with supervised and unsupervised machine learning concepts, in addition to providing you with an overview of IBM Cloud and Watson Machine Learning. You'll gain insights into running various techniques, such as K-means clustering, K-nearest neighbor (KNN), and time series prediction in IBM Cloud with real-world examples. The book will then help you delve into creating a Spark pipeline in Watson Studio. You will also be guided through deep learning and neural network principles on the IBM Cloud using TensorFlow. With the help of NLP techniques, you can then brush up on building a chatbot. In later chapters, you will cover three powerful case studies, including the facial expression classification platform, the automated classification of lithofacies, and the multi-biometric identity authentication platform, helping you to become well versed with these methodologies. By the end of this book, you will be ready to build efficient machine learning solutions on the IBM Cloud and draw insights from the data at hand using real-world examples. What you will learn * Understand key characteristics of IBM machine learning services * Run supervised and unsupervised techniques in the cloud * Understand how to create a Spark pipeline in Watson Studio * Implement deep learning and neural networks on the IBM Cloud with TensorFlow * Create a complete, cloud-based facial expression classification solution * Use biometric traits to build a cloud-based human identification system Who this book is for This beginner-level book is for data scientists and machine learning engineers who want to get started with IBM Cloud and its machine learning services using practical examples. Basic knowledge of Python and some understanding of machine learning will be useful.

目录

About Packt

Why subscribe?

Packt.com

Contributors

About the author

About the reviewer

Packt is searching for authors like you

Preface

Who this book is for

What this book covers

To get the most out of this book

Download the example code files

Download the color images

Conventions used

Get in touch

Reviews

Section 1: Introduction and Foundation

Introduction to IBM Cloud

Understanding IBM Cloud

Prerequisites

Accessing the IBM Cloud

Cloud resources

The IBM Cloud and Watson Machine Learning services

Setting up the environment

Watson Studio Cloud

Watson Studio architecture and layout

Establishing context

Setting up a new project

Data visualization tutorial

Summary

Feature Extraction - A Bag of Tricks

Preprocessing

The data refinery

Data

Adding the refinery

Refining data by using commands

Dimensional reduction

Data fusion

Catalog setup

Recommended assets

A bag of tricks

Summary

Supervised Machine Learning Models for Your Data

Model selection

IBM Watson Studio Model Builder

Using the model builder

Training data

Guessing which technique to use

Deployment

Model builder deployment steps

Testing the model

Continuous learning and model evaluation

Classification

Binary classification

Multiclass classification

Regression

Testing the predictive capability

Summary

Implementing Unsupervised Algorithms

Unsupervised learning

Watson Studio, machine learning flows, and KMeans

Getting started

Creating an SPSS modeler flow

Additional node work

Training and testing

SPSS flow and K-means

Exporting model results

Semi-supervised learning

Anomaly detection

Machine learning based approaches

Online or batch learning

Summary

Section 2: Tools and Ingredients for Machine Learning in IBM Cloud

Machine Learning Workouts on IBM Cloud

Watson Studio and Python

Setting up the environment

Try it out

Data cleansing and preparation

K-means clustering using Python

The Python code

Observing the results

Implementing in Watson

Saving your work

K-nearest neighbors

The Python code

Implementing in Watson

Exploring Markdown text

Time series prediction example

Time series analysis

Setup

Data preprocessing

Indexing for visualization

Visualizations

Forecasting sales

Validation

Summary

Using Spark with IBM Watson Studio

Introduction to Apache Spark

Watson Studio and Spark

Creating a Spark-enabled notebook

Creating a Spark pipeline in Watson Studio

What is a pipeline?

Pipeline objectives

Breaking down a pipeline example

Data preparation

The pipeline

A data analysis and visualization example

Setup

Getting the data

Loading the data

Exploration

Extraction

Plotting

Saving

Downloading your notebook

Summary

Deep Learning Using TensorFlow on the IBM Cloud

Introduction to deep learning

TensorFlow basics

Neural networks and TensorFlow

An example

Creating the new project

Notebook asset type

Running the imported notebook

Reviewing the notebook

TensorFlow and image classifications

Adding the service

Required modules

Using the API key in code

Additional preparation

Upgrading Watson

Images

Code examination

Accessing the model

Detection

Classification and output

Objects detected

Now the fun part

Save and share your work

Summary

Section 3: Real-Life Complete Case Studies

Creating a Facial Expression Platform on IBM Cloud

Understanding facial expression classification

Face detection

Facial expression analysis

TBM

Exploring expression databases

Training with the Watson Visual Recognition service

Preprocessing faces

Preparing the training data

Negative or non-positive classing

Preparing the environment

Project assets

Creating classes for our model

Automatic labeling

Learning the expression classifier

Evaluating the expression classifier

Viewing the model training results

Testing the model

Test scores

Test the model

Improving the model

More training data

Adding more classes

Results

Summary

The Automated Classification of Lithofacies Formation Using ML

Understanding lithofacies

Depositional environments

Lithofacies formation

Our use case

Exploring the data

Well logging

Log ASCII Standard (LAS)

Loading the data asset

Data asset annotations

Profiling the data

Using a notebook and Python instead

Loading the data

Visualizations

Box plotting

Histogram

The scatter matrix

Training the classifier

Building a logistic regression model

Building a KNN model

Building a Gaussian Naive Bayes model

Building a support vector machine model

Building a decision tree model

Summing them up

Evaluating the classifier

A disclaimer of sorts

Understanding decision trees

Summary

Building a Cloud-Based Multibiometric Identity Authentication Platform

Understanding biometrics

Making a case

Popular use cases

Privacy concerns

Components of a biometric authentication solution

Exploring biometric data

Specific Individual identification

The Challenge of Biometric Data Use

Sample sizing

Feature extraction

Biometric recognition

Multimodal fusion

Our example

Premise

Data preparation

Project setup

Creating classes

Training the model

Testing our project

Guidelines for good training

Implementation

Summary

Another Book You May Enjoy

Leave a review - let other readers know what you think