Introducing Machine Learning

Introducing Machine Learning

by Dino Esposito, Francesco Esposito
Released February 2020
Publisher(s): Microsoft Press
ISBN: 9780135588338

Read it now on the O’Reilly learning platform with a 10-day free trial.

O’Reilly members get unlimited access to live online training experiences, plus books, videos, and digital content from O’Reilly and nearly 200 trusted publishing partners.

Start your free trial

Book description

Master machine learning concepts and develop real-world solutions

Machine learning offers immense opportunities, and Introducing Machine Learning delivers practical knowledge to make the most of them. Dino and Francesco Esposito start with a quick overview of the foundations of artificial intelligence and the basic steps of any machine learning project. Next, they introduce Microsoft’s powerful ML.NET library, including capabilities for data processing, training, and evaluation. They present families of algorithms that can be trained to solve real-life problems, as well as deep learning techniques utilizing neural networks. The authors conclude by introducing valuable runtime services available through the Azure cloud platform and consider the long-term business vision for machine learning.

· 14-time Microsoft MVP Dino Esposito and Francesco Esposito help you

· Explore what’s known about how humans learn and how intelligent software is built

· Discover which problems machine learning can address

· Understand the machine learning pipeline: the steps leading to a deliverable model

· Use AutoML to automatically select the best pipeline for any problem and dataset

· Master ML.NET, implement its pipeline, and apply its tasks and algorithms

· Explore the mathematical foundations of machine learning

· Make predictions, improve decision-making, and apply probabilistic methods

· Group data via classification and clustering

· Learn the fundamentals of deep learning, including neural network design

· Leverage AI cloud services to build better real-world solutions faster

About This Book

· For professionals who want to build machine learning applications: both developers who need data science skills and data scientists who need relevant programming skills

· Includes examples of machine learning coding scenarios built using the ML.NET library

Table of contents

  1. Cover Page
  2. Title Page
  3. Copyright Page
  4. Dedications
  5. Contents at a Glance
  6. Contents
  7. Acknowledgments
  8. About the Authors
  9. Introduction
    1. Who Should Read This Book?
    2. Who Should Not Read This Book?
    3. Organization of This Book
    4. Code Samples
    5. Errata and Book Support
    6. Stay in Touch
  10. Part I: Laying the Groundwork of Machine Learning
    1. Chapter 1. How Humans Learn
      1. The Journey Toward Thinking Machines
      2. The Biology of Learning
      3. Artificial Forms of Intelligence
      4. Summary
    2. Chapter 2. Intelligent Software
      1. Applied Artificial Intelligence
      2. General Artificial Intelligence
      3. Summary
    3. Chapter 3. Mapping Problems and Algorithms
      1. Fundamental Problems
      2. More Complex Problems
      3. Automated Machine Learning
      4. Summary
    4. Chapter 4. General Steps for a Machine Learning Solution
      1. Data Collection
      2. Data Preparation
      3. Model Selection and Training
      4. Deployment of the Model
      5. Summary
    5. Chapter 5. The Data Factor
      1. Data Quality
      2. Data Integrity
      3. What’s a Data Scientist, Anyway?
      4. Summary
  11. Part II: Machine Learning in .NET
    1. Chapter 6. The .NET Way
      1. Why (Not) Python?
      2. Introducing ML.NET
      3. Summary
    2. Chapter 7. Implementing the ML.NET Pipeline
      1. The Data to Start From
      2. The Training Step
      3. Price Prediction from Within a Client Application
      4. Summary
    3. Chapter 8. ML.NET Tasks and Algorithms
      1. The Overall ML.NET Architecture
      2. Classification Tasks
      3. Clustering Tasks
      4. Transfer Learning
      5. Summary
  12. Part III: Fundamentals of Shallow Learning
    1. Chapter 9. Math Foundations of Machine Learning
      1. Under the Umbrella of Statistics
      2. Bias and Variance
      3. Data Representation
      4. Summary
    2. Chapter 10. Metrics of Machine Learning
      1. Statistics vs. Machine Learning
      2. Evaluation of a Machine Learning Model
      3. Preparing Data for Processing
      4. Summary
    3. Chapter 11. How to Make Simple Predictions: Linear Regression
      1. The Problem
      2. The Linear Algorithm
      3. Improving the Solution
      4. Summary
    4. Chapter 12. How to Make Complex Predictions and Decisions: Trees
      1. The Problem
      2. Design Principles for Tree-Based Algorithms
      3. Classification Trees
      4. Regression Trees
      5. Summary
    5. Chapter 13. How to Make Better Decisions: Ensemble Methods
      1. The Problem
      2. The Bagging Technique
      3. The Boosting Technique
      4. Summary
    6. Chapter 14. Probabilistic Methods: Naïve Bayes
      1. Quick Introduction to Bayesian Statistics
      2. Applying Bayesian Statistics to Classification
      3. Naïve Bayes Classifiers
      4. Naïve Bayes Regression
      5. Summary
    7. Chapter 15. How to Group Data: Classification and Clustering
      1. A Basic Approach to Supervised Classification
      2. Support Vector Machine
      3. Unsupervised Clustering
      4. Summary
  13. Part IV: Fundamentals of Deep Learning
    1. Chapter 16. Feed-Forward Neural Networks
      1. A Brief History of Neural Networks
      2. Types of Artificial Neurons
      3. Training a Neural Network
      4. Summary
    2. Chapter 17. Design of a Neural Network
      1. Aspects of a Neural Network
      2. Building a Neural Network
      3. Summary
    3. Chapter 18. Other Types of Neural Networks
      1. Common Issues of Feed-Forward Neural Networks
      2. Recurrent Neural Networks
      3. Convolutional Neural Networks
      4. Further Neural Network Developments
      5. Summary
    4. Chapter 19. Sentiment Analysis: An End-to-End Solution
      1. Preparing Data for Training
      2. Training the Model
      3. The Client Application
      4. Summary
  14. Part V: Final Thoughts
    1. Chapter 20. AI Cloud Services for the Real World
      1. Azure Cognitive Services
      2. Azure Machine Learning Studio
      3. On-Premises Services
      4. Microsoft Data Processing Services
      5. Summary
    2. Chapter 21. The Business Perception of AI
      1. Perception of AI in the Industry
      2. End-to-End Solutions
      3. Summary
  15. Index
  16. Code Snippets

Product information

  • Title: Introducing Machine Learning
  • Author(s): Dino Esposito, Francesco Esposito
  • Release date: February 2020
  • Publisher(s): Microsoft Press
  • ISBN: 9780135588338