Book Image

Hands-On Machine Learning with C#

By : Matt R. Cole
Book Image

Hands-On Machine Learning with C#

By: Matt R. Cole

Overview of this book

<p>The necessity for machine learning is everywhere, and most production enterprise applications are written in C# using tools such as Visual Studio, SQL Server, and Microsoft Azur2e. Hands-On Machine Learning with C# uniquely blends together an understanding of various machine learning concepts, techniques of machine learning, and various available machine learning tools through which users can add intelligent features.These tools include image and motion detection, Bayes intuition, and deep learning, to C# .NET applications.</p> <p>Using this book, you will learn to implement supervised and unsupervised learning algorithms and will be better equipped to create excellent predictive models. In addition, you will learn both supervised and unsupervised forms of regression, mainly logistic and linear regression, in depth. Next, you will use the nuML machine learning framework to learn how to create a simple decision tree. In the concluding chapters, you will use the Accord.Net machine learning framework to learn sequence recognition of handwritten numbers using dynamic time warping. We will also cover advanced concepts such as artificial neural networks, autoencoders, and reinforcement learning.</p> <p>By the end of this book, you will have developed a machine learning mindset and will be able to leverage C# tools, techniques, and packages to build smart, predictive, and real-world business applications.</p>

Related Content you might be interested in

Current Title:

Small book image
Hands-On Machine Learning with C#
Matt R. Cole
May, 2018 | 274 pages
No titles found
Table of Contents (14 chapters)
Preface
Preface
Who this book is for
What this book covers
To get the most out of this book
Get in touch
Free Chapter
1
Machine Learning Basics
Machine Learning Basics
Introduction to machine learning
Data mining
Artificial Intelligence
Bio-AI
Deep learning
Probability and statistics
Approaching your machine learning project
Iris dataset
Supervised learning
Unsupervised learning
Reinforcement learning
Build, buy, or open source
Additional reading
Summary
References
2
ReflectInsight – Real-Time Monitoring
ReflectInsight – Real-Time Monitoring
Router
Log Viewer
Live Viewer
Summary
3
Bayes Intuition – Solving the Hit and Run Mystery and Performing Data Analysis
Bayes Intuition – Solving the Hit and Run Mystery and Performing Data Analysis
Overviewing Bayes' theorem
Overviewing Naive Bayes and plotting data
Summary
References
4
Risk versus Reward – Reinforcement Learning
Risk versus Reward – Reinforcement Learning
Overviewing reinforcement learning
Types of learning
Q-learning
SARSA
Running our application
Tower of Hanoi
Summary
References
5
Fuzzy Logic – Navigating the Obstacle Course
Fuzzy Logic – Navigating the Obstacle Course
Fuzzy logic
Summary
References
6
Color Blending – Self-Organizing Maps and Elastic Neural Networks
Color Blending – Self-Organizing Maps and Elastic Neural Networks
Under the hood of an SOM
Summary
7
Facial and Motion Detection – Imaging Filters
Facial and Motion Detection – Imaging Filters
Facial detection
Motion detection
Summary
8
Encyclopedias and Neurons – Traveling Salesman Problem
Encyclopedias and Neurons – Traveling Salesman Problem
Traveling salesman problem
Learning rate parameter
Summary
9
Should I Take the Job – Decision Trees in Action
Should I Take the Job – Decision Trees in Action
Decision tree
Should I take the job?
numl
Accord.NET decision trees
Summary
References
10
Deep Belief – Deep Networks and Dreaming
Deep Belief – Deep Networks and Dreaming
Restricted Boltzmann Machines
What does a computer dream?
Summary
References
11
Microbenchmarking and Activation Functions
Microbenchmarking and Activation Functions
Visual activation function plotting
Summary
12
Intuitive Deep Learning in C# .NET
Intuitive Deep Learning in C# .NET
What is deep learning?
The Kelp.Net Framework
Summary
References
13
Quantum Computing – The Future
Quantum Computing – The Future
Superposition
Teleportation
Summary

Facial detection

Let's start out with facial detection. In our example, I'm going to use my friendly little French Bulldog, Frenchie, as our assistant. Tried to get my beautiful wife to do the honors but makeup, hair; well, I'm sure you know that story! Frenchie the Bulldog, however, had no complaints.

Before I start, please re-read the chapter title. No matter how many times you read it, you'll probably miss the key point here, and it's so very important. Notice it says facial detection and not facial recognition. This is so very important that I needed to stop and re-stress it. We are not trying to identify Joe, Bob, or Sally. We are trying to identify that, out of everything we see via our camera, we can detect a face. We are not concerned with whose face it is, just the fact that it is a face! It is so important that we understand this before moving...

Previous Section
End of Section 2
Next Section