Chapter 1, A Quick Refresher, give you a basic refresher on neural networks.

Chapter 2,  Building our First Neural Network Together, shows what activations are, what their purpose is, and how they appear visually. We will also present a small C# application to visualize each using open source packages such as Encog, Aforge, and Accord.

Chapter 3,  Decision Trees and Random Forests, helps you to understand what decision trees and random forests are and how they can be used.

Chapter 4, Face and Motion Detection, will have you use the Accord.Net machine learning framework to connect to your local video recording device and capture real-time images of whatever is within the camera's field of view. Any face in the field of view will be then tracked.

Chapter 5, Training CNNs Using ConvNetSharp, will focus on how to train CNNs with the open source package ConvNetSharp. Examples will be used to illustrate the concepts for the user.

Chapter 6, Training Autoencoders Using RNNSharp, will have you use the autoencoders of the open source package RNNSharp to parse and handle various corpuses of text.

Chapter 7, Replacing Back Propagation with PSO, presents how particle swarm optimization can replace neural network training methods such as back propagation for training a neural network.

Chapter 8, Function Optimizations: How and Why, introduces you to function optimization, which is an integral part of every neural network.

Chapter 9, Finding Optimal Parameters, will show you how to easily find the most optimal parameters for your neural network functions using Numeric and Heuristic Optimization techniques.

Chapter 10, Object Detection with TensorFlowSharp, will expose the reader to the open source package TensorFlowSharp.

Chapter 11, Time Series Prediction and LSTM Using CNTK, will see you using the Microsoft Cognitive Toolkit, formerly known as CNTK, as well as long short-term memory (LSTM), to accomplish time series prediction.

Chapter 12, GRUs Compared to LSTMs, RNNs, and Feedforward Networks, deals with Gated Recurrent Units (GRUs), including how they compare to other types of neural network.

Appendix A, Activation Function Timings, shows different activation functions and their respective plots.

Appendix B, Function Optimization Reference, includes different optimization functions.