What do you get with Print?

Instant access to your digital copy whilst your Print order is Shipped

Paperback book shipped to your preferred address

Redeem a companion digital copy on all Print orders

Access this title in our online reader with advanced features

DRM FREE - Read whenever, wherever and however you want

A Quick Refresher

Welcome to Hands-On Neural Network Development Using C#. I want to thank you for purchasing this book and for taking this journey with us. It seems as if, everywhere you turn, everywhere you go, all you hear and read about is machine learning, artificial intelligence, deep learning, neuron this, artificial that, and on and on. And, to add to all that excitement, everyone you talk to has a slightly different idea about the meaning of each of those terms.

In this chapter, we are going to go over some very basic neural network terminology to set the stage for future chapters. We need to be speaking the same language, just to make sure that everything we do in later chapters is crystal clear.

I should also let you know that the goal of the book is to get you, a C# developer, up and running as fast as possible. To do this, we will use as many open source libraries as possible. We must do a few custom applications, but we've provided the source code for these as well. In all cases, we want you to be able to add this functionality to your applications with maximal speed and minimal effort.

OK, let's begin.

Neural networks have been around for very many years but have made a resurgence over the past few years and are now a hot topic. And that, my friends, is why this book is being written. The goal here is to help you get through the weeds and into the open so you can navigate your neural path to success. There is a specific focus in this book on C# .NET developers. I wanted to make sure that the C# developers out there had handy resources that could be of some help in their projects, rather than the Python, R, and MATLAB code we more commonly see. If you have Visual Studio installed and a strong desire to learn, you are ready to begin your journey.

First, let's make sure we're clear on a couple of things. In writing this book, the assumption was made that you, the reader, had limited exposure to neural networks. If you do have some exposure, that is great; you may feel free to jump to the sections that interest you the most. I also assumed that you are an experienced C# developer, and have built applications using C#, .NET, and Visual Studio, although I made no assumptions as to which versions of each you may have used. The goal is not about C# syntax, the .NET framework, or Visual Studio itself. Once again, the purpose is to get as many valuable resources into the hands of developers, so they can embellish their code and create world-class applications.

Now that we've gotten that out of the way, I know you're excited to jump right in and start coding, but to make you productive, we first must spend some time going over some basics. A little bit of theory, some fascinating insights into the whys and wherefores, and we're going to throw in a few visuals along the way to help with the rough-and-tough dry stuff. Don't worry; we won't go too deep on the theory, and, in a few pages from here, you'll be writing and going through source code!

Also, keep in mind that research in this area is rapidly evolving. What is the latest and greatest today is old news next month. Therefore, consider this book an overview of different research and opinions. It is not the be-all-and-end-all bible of everything neural network-related, nor should it be perceived to be. You are very likely to encounter someone else with different opinions from that of the writer. You're going to find people who will write apps and functions differently. That's great—gather all the information that you can, and make informed choices on your own. Only doing by that will you increase your knowledge base.

This chapter will include the following topics:

Neural network overview
The role of neural networks in today's enterprises
Types of learning
Understanding perceptions
Understanding activation functions
Understanding back propagation

Neural network overview

Let's start by defining exactly what we are going to call a neural network. Let me first note that you may also hear a neural network called an Artificial Neural Network (ANN). Although personally I do not like the term artificial, we'll use those terms interchangeably throughout this book.

"Let's state that a neural network, in its simplest form, is a system comprising several simple but highly interconnected elements; each processes information based upon their response to external inputs."

Did you know that neural networks are more commonly, but loosely, modeled after the cerebral cortex of a mammalian brain? Why didn't I say that they were modeled after humans? Because there are many instances where biological and computational studies are used from brains from rats, monkeys, and, yes, humans. A large neural network may have hundreds or maybe even thousands of processing units, where as a mammalian brain has billions. It's the neurons that do the magic, and we could in fact write an entire book on that topic alone.

Here's why I say they do all the magic: If I showed you a picture of Halle Berry, you would recognize her right away. You wouldn't have time to analyze things; you would know based upon a lifetime of collected knowledge. Similarly, if I said the word pizza to you, you would have an immediate mental image and possibly even start to get hungry. How did all that happen just like that? Neurons! Even though the neural networks of today continue to gain in power and speed, they pale in comparison to the ultimate neural network of all time, the human brain. There is so much we do not yet know or understand about this neural network; just wait and see what neural networks will become once we do!

Neural networks are organized into layers made up of what are called nodes or neurons. These nodes are the neurons themselves and are interconnected (throughout this book we use the terms nodes and neurons interchangeably). Information is presented to the input layer, processed by one or more hidden layers, then given to the output layer for final (or continued further) processing—lather, rinse, repeat!

But what is a neuron, you ask? Using the following diagram, let's state this:

"A neuron is the basic unit of computation in a neural network"

As I mentioned earlier, a neuron is sometimes also referred to as a node or a unit. It receives input from other nodes or external sources and computes an output. Each input has an associated weight (w1 and w2 below), which is assigned based on its relative importance to the other inputs. The node applies a function f (an activation function, which we will learn more about later on) to the weighted sum of its inputs. Although that is an extreme oversimplification of what a neuron is and what it can do, that's basically it.

Let's look visually at the progression from a single neuron into a very deep learning network. Here is what a single neuron looks like visually based on our description:

Next, the following diagram shows a very simple neural network comprised of several neurons:

Here is a somewhat more complicated, or deeper, network:

Neural network training

Now that we know what a neural network and neurons are, we should talk about what they do and how they do it. How does a neural network learn? Those of you with children already know the answer to this one. If you want your child to learn what a cat is, what do you do? You show them cats (pictures or real). You want your child to learn what a dog is? Show them dogs. A neural network is conceptually no different. It has a form of learning rule that will modify the incoming weights from the input layer, process them through the hidden layers, put them through an activation function, and hopefully will be able to identify, in our case, cats and dogs. And, if done correctly, the cat does not become a dog!

One of the most common learning rules with neural networks is what is known as the delta rule. This is a supervised rule that is invoked each time the network is presented with another learning pattern. Each time this happens it is called a cycle or epoch. The invocation of the rule will happen each time that input pattern goes through one or more forward propagation layers, and then through one or more backward propagation layers.

More simply put, when a neural network is presented with an image it tries to determine what the answer might be. The difference between the correct answer and our guess is the error or error rate. Our objective is that the error rate gets either minimized or maximized. In the case of minimization, we need the error rate to be as close to 0 as possible for each guess. The closer we are to 0, the closer we are to success.

As we progress, we undertake what is termed a gradient descent, meaning we continue along toward what is called the global minimum, our lowest possible error, which hopefully is paramount to success. We descend toward the global minimum.

Once the network itself is trained, and you are happy, the training cycle can be put to bed and you can move on to the testing cycle. During the testing cycle, only the forward propagation layer is used. The output of this process results in the model that will be used for further analysis. Again, no back propagation occurs during testing.

A visual guide to neural networks

In this section, I could type thousands of words trying to describe all of the combinations of neural networks and what they look like. However, no amount of words would do any better than the diagram that follows:

Reprinted with permission, Copyright Asimov Institute
Source: http://www.asimovinstitute.org/neural-network-zoo/

Let's talk about a few of the more common networks from the previous diagram:

Perceptron: This is the simplest feed-forward neural network available, and, as you can see, it does not contain any hidden layers:

Feed-forward network: This network is perhaps the simplest type of artificial neural network devised. It contains multiple neurons (nodes) arranged in layers. Nodes from adjacent layers have connections or edges between them. Each connection has weights associated with them:

Recurrent neural network (RNN): RNNs are called recurrent because they perform the same task for every element of a sequence, with the output depending on the previous computations. They are also able to look back at previous steps, which form a sort of short-term memory:

Key benefits

Get a strong foundation of neural networks with access to various machine learning and deep learning libraries

Real-world case studies illustrating various neural network techniques and architectures used by practitioners

Cutting-edge coverage of Deep Networks, optimization algorithms, convolutional networks, autoencoders and many more

Description

Neural networks have made a surprise comeback in the last few years and have brought tremendous innovation in the world of artificial intelligence. The goal of this book is to provide C# programmers with practical guidance in solving complex computational challenges using neural networks and C# libraries such as CNTK, and TensorFlowSharp. This book will take you on a step-by-step practical journey, covering everything from the mathematical and theoretical aspects of neural networks, to building your own deep neural networks into your applications with the C# and .NET frameworks. This book begins by giving you a quick refresher of neural networks. You will learn how to build a neural network from scratch using packages such as Encog, Aforge, and Accord. You will learn about various concepts and techniques, such as deep networks, perceptrons, optimization algorithms, convolutional networks, and autoencoders. You will learn ways to add intelligent features to your .NET apps, such as facial and motion detection, object detection and labeling, language understanding, knowledge, and intelligent search. Throughout this book, you will be working on interesting demonstrations that will make it easier to implement complex neural networks in your enterprise applications.

Who is this book for?

This book is for Machine Learning Engineers, Data Scientists, Deep Learning Aspirants and Data Analysts who are now looking to move into advanced machine learning and deep learning with C#. Prior knowledge of machine learning and working experience with C# programming is required to take most out of this book

What you will learn

•Understand perceptrons and how to implement them in C#

•Learn how to train and visualize a neural network using cognitive services

•Perform image recognition for detecting and labeling objects using C# and TensorFlowSharp

•Detect specific image characteristics such as a face using Accord.Net

•Demonstrate particle swarm optimization using a simple XOR problem and Encog

•Train convolutional neural networks using ConvNetSharp

•Find optimal parameters for your neural network functions using numeric and heuristic optimization techniques.

What do you get with Print?

Instant access to your digital copy whilst your Print order is Shipped

Paperback book shipped to your preferred address

Redeem a companion digital copy on all Print orders

Access this title in our online reader with advanced features

DRM FREE - Read whenever, wherever and however you want

Frequently bought together

Hands-On Network Programming with C# and .NET Core

€32.99

Hands-On Neural Network Programming with C#

€32.99

Total € 65.98

MrBigBeast Feb 10, 2020

The book presents (sort of) code for a neural network.The good: it's all in C# without requiring outside packages. Interesting reference stuff towards the end.the bad: the code is cute, using lots of little C# specific tricks. Good luck porting this Java. One class appears on page 35, then its constructor is introduced a dozen or so pages later. Why? Code notes aren't commented.Why couldn't the author just cut and paste his actual code?The Packt Publishing outfit claims you can download the code from their web site. The site is dead. Once you register and agree to allow cookies, nothing works. The links that do respond take forever. Not a good sign for a publisher of programming books...

Amazon Verified review

Hands-On Neural Network Programming with C#: Add powerful neural network capabilities to your C# enterprise applications

What do you get with Print?

Hands-On Neural Network Programming with C#

A Quick Refresher

Technical requirements

Neural network overview

Neural network training

A visual guide to neural networks

The role of neural networks in today's enterprises

Types of learning

Supervised learning

Unsupervised learning

Reinforcement learning

Page 1 of 10

Key benefits

Description

Who is this book for?

What you will learn

Product Details

What do you get with Print?

Product Details

Frequently bought together

Table of Contents

Recommendations for you

Customer reviews

People who bought this also bought

About the author

FAQs

Hands-On Neural Network Programming with C#: Add powerful neural network capabilities to your C# enterprise applications

What do you get with Print?

Contact Details

Shipping Address

Billing Address

Key benefits

Description

Who is this book for?

What you will learn

Product Details

What do you get with Print?

Contact Details

Shipping Address

Billing Address

Product Details

Packt Subscriptions

Frequently bought together

Table of Contents

Recommendations for you

Customer reviews

People who bought this also bought

About the author

FAQs