Chapter 1, Machine Learning Basics, provides an introduction to machine learning as well as what we hope to accomplish in this book.
Chapter 2, ReflectInsight – Real-Time Monitoring, introduces ReflectInsight, a powerful, flexible, and rich framework that we will use throughout the book for logging and insight into our algorithms.
Chapter 3, Bayes Intuition – Solving the Hit and Run Mystery and Performing Data Analysis, exposes the reader to Bayes intuition. We will also examine and solve the famous "hit and run" problem, where we try to determine who fled the scene of an accident.
Chapter 4, Risk versus Reward – Reinforcement Learning, shows how reinforcement learning works.
Chapter 5, Fuzzy Logic – Navigating the Obstacle Course, implements fuzzy logic to guide our autonomous guided vehicle around an obstacle course. We'll show how to load various maps, and how our autonomous vehicle receives rewards and penalties for making correct and incorrect decisions.
Chapter 6, Color Blending – Self-Organizing Maps and Elastic Neural Networks, exposes the reader to the power of SOM by showing how we can take random colors and blend them together. This provides the reader with a very simple intuition regarding Self Organizing Maps.
Chapter 7, Facial and Motion Detection – Imaging Filters, give the reader a very simple framework to quickly add facial and motion detection capabilities to their program. We provide various examples of both facial and motion detection, explain various algorithms we will use, and meet Frenchie, our dedicated French Bulldog Assistant!
Chapter 8, Encyclopedias and Neurons – Traveling Salesman Problem, uses neurons to solve the age-old Traveling Salesman Problem, where our salesman has been given a map of houses he must visit in order to sell encyclopedias. In order to meet his goals, he must choose the shortest path while only visiting each house once, and end up back where he started.
Chapter 9, Should I Take the Job – Decision Trees in Action, exposes the reader to decision trees using two different open source frameworks. We will use decision trees to answer the question, Should I Take the Job?
Chapter 10, Deep Belief - Deep Networks and Dreaming, covers an open source framework SharpRBM. We will delve into the world of Boltzmann and Restricted Boltzmann machines. We will ask and answer the question, What do computers dream when they dream?
Chapter 11, Microbenchmarking and Activation Functions, exposes the reader to Benchmark.Net, an open source microbenchmarking framework. We will show the reader how to benchmark code and functions. We will also explain what an activation function is and show how we have microbenchmarked many of the activation functions in use today. The reader will gain valuable insights into the time each function takes, as well as the timing difference between using floats and doubles.
Chapter 12, Intuitive Deep Learning in C# .NET, covers an open source framework named Kelp.Net. This framework is the most powerful deep learning framework available for C# .NET developers. We will show the reader how to perform many operations and tests using the framework, and integrate this with ReflectInsight to get incredible, rich information about our deep learning algorithms.
Chapter 13, Quantum Computing – The Future, expose the reader to the future, the world of quantum computing.