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.
Table of Contents (16 chapters)
13
Activation Function Timings

Time Series Prediction and LSTM Using CNTK

This chapter is dedicated to helping you understand more of the Microsoft Cognitive Toolkit, or CNTK. The inspiration for the examples contained within this chapter comes from the Python version of CNTK 106: Part A – Time Series prediction with LSTM (Basics). As C# developers, the Python code is not what we will be using (although there are several ways in which we could) so we made our own C# example to mirror that tutorial. To make our example easy and intuitive, we will use the Sine function to predict future time-series data. Specifically, and more concretely, we will be using a long short-term memory recurrent neural network, sometimes called an LSTM-RNN or just LSTM. There are many variants of the LSTM; we will be working with the original.

In this chapter, we will cover the following topics:

  • LSTM
  • Tensors
  • Static and dynamic...