Book Image

Hands-On Neural Network Programming with C#

By : Matt Cole
Book Image

Hands-On Neural Network Programming with C#

By: Matt Cole

Overview of this book

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.

Related Content you might be interested in

Current Title:

Small book image
Hands-On Neural Network Programming with C#
Matt Cole
Sep, 2018 | 328 pages
Small book image
Learn ARCore - Fundamentals of Google ARCore
Micheal Lanham
Mar, 2018 | 274 pages
Small book image
Hands-On Genetic Algorithms with Python
Eyal Wirsansky
Jan, 2020 | 346 pages
Small book image
Deep Learning with Hadoop
Dipayan Dev
Feb, 2017 | 206 pages
Table of Contents (16 chapters)
Preface
Preface
Who this book is for
What this book covers
To get the most out of this book
Code in Action
Get in touch
Free Chapter
1
A Quick Refresher
A Quick Refresher
Technical requirements
Neural network overview
The role of neural networks in today's enterprises
Types of learning
Understanding perceptrons
Understanding activation functions
Understanding back propagation
Summary
References
2
Building Our First Neural Network Together
Building Our First Neural Network Together
Technical requirements
Our neural network
Neural network training
Neural network functions
The neural network
Examples
Summary
3
Decision Trees and Random Forests
Decision Trees and Random Forests
Technical requirements
Decision trees
Random forests
SharpLearning
Example code and applications
Summary
References
4
Face and Motion Detection
Face and Motion Detection
Technical requirements
Facial detection
Motion detection
Summary
5
Training CNNs Using ConvNetSharp
Training CNNs Using ConvNetSharp
Technical requirements
Getting acquainted
Filters
Creating a network
GPU
Fluent training with the MNIST database
Training the network
Summary
References
6
Training Autoencoders Using RNNSharp
Training Autoencoders Using RNNSharp
Technical requirements
What is an autoencoder?
Different types of autoencoder
Creating your own autoencoder
Summary
References
7
Replacing Back Propagation with PSO
Replacing Back Propagation with PSO
Technical requirements
Basic theory
Replacing back propagation with Particle Swarm Optimization
Summary
8
Function Optimizations: How and Why
Function Optimizations: How and Why
Technical requirements
Getting started
Function minimization and maximization
Hyperparameters and tuning
Understanding visualizations
Plotting results
Adding new optimization functions
Summary
9
Finding Optimal Parameters
Finding Optimal Parameters
Technical requirements
Optimization
Optimization methods
Parallelism
Summary
References
10
Object Detection with TensorFlowSharp
Object Detection with TensorFlowSharp
Technical requirements
Working with Tensors
Developing your own TensorFlow application
Detecting images
Summary
References
11
Time Series Prediction and LSTM Using CNTK
Time Series Prediction and LSTM Using CNTK
Technical requirements
Long short-term memory
CNTK terminology
Our example
How well do LSTMs perform?
Summary
References
12
GRUs Compared to LSTMs, RNNs, and Feedforward networks
GRUs Compared to LSTMs, RNNs, and Feedforward networks
Technical requirements
QuickNN
Understanding GRUs
Differences between LSTM and GRU
Coding different networks
Comparing LSTM, GRU, Feedforward, and RNN operations
Network differences
Summary
13
Activation Function Timings
Activation Function Timings
14
Function Optimization Reference
Function Optimization Reference
The Currin Exponential function
The Webster function
The Oakley & O'Hagan function
The Grammacy function
Franke's function
The Lim function
The Ackley function
The Bukin function N6
The Cross-In-Tray function
The Drop-Wave function
The Eggholder function
The Holder Table function
The Levy function
The Levy function N13
The Rastrigin function
The Schaffer function N.2
The Schaffer function N.4
The Shubert function
The Rotated Hyper-Ellipsoid function
The Sum Squares function
The Booth function
The Mccormick function
The Power Sum function
The Three-Hump Camel function
The Easom function
The Michalewicz function
The Beale function
The Goldstein-Price function
The Perm function
The Griewank function
The Bohachevsky function
The Sphere function
The Rosenbrock function
The Styblinski-Tang function
Summary
Keep reading
15
Other Books You May Enjoy
Other Books You May Enjoy
Leave a review - let other readers know what you think

Object Detection with TensorFlowSharp

In this chapter, we are going to introduce you to an open source package called TensorFlowSharp. More specifically, we will be using the TensorFlow[1] Object Detection API, which is an open source framework built on top of TensorFlow, which makes it easy to construct, train, and deploy various forms of object detection models.

For those not familiar with TensorFlow, the following is an excerpt from the TensorFlow website[2]:

"TensorFlow is an open source software library for high performance numerical computation. Its flexible architecture allows easy deployment of computation across a variety of platforms (such as CPUs, GPUs, and TPUs), and from desktops to clusters of servers to mobile and edge devices. Originally developed by researchers and engineers from the Google Brain team within Google's AI organization, it comes with strong...
Previous Section
End of Section 1
Next Section