What you'll learn

Basic theory of Multi-Layer Neural Networks

The mathematics of Neural Network Training: Backpropagation and Gradient Descent

The mathematics of Neuron Activation Functions

How to implement in C# the Training and Testing of a Multi-Layer Neural Network

How to create Datasets for Training and Testing the Neural Network

Requirements

Basic understanding of Linear Algebra

Intermediate proficiency in C#

Basic knowledge of JSON

Description

This course presents in detail the implementation of multi-layer neural network training and testing. The steps involved in neural network training and testing are discussed in detail with thorough review of the mathematics. The C# source code, that is available for download, is discussed in detail. Testing with datasets is presented with the aim of being applicable to any prediction problem use case. The course begins with a thorough introduction to neural networks, provides a detailed view of the structure of multi-layer neural networks, presents the mathematics involved in neural network training in a very simple and methodical approach, presents the demonstration of testing with a number of datasets, and ends with a quick summary of neural network training.What you will learn in the CourseBasic theory of Multi-Layer Neural NetworksThe mathematics of Neural Network Training: Backpropagation and Gradient DescentThe mathematics of Neuron Activation FunctionsThe process for training and testing the Neural NetworkHow to implement in C# the Training and Testing of a Multi-Layer Neural NetworkHow to create Datasets for Training and Testing the Neural NetworkCourse OutlineSection 1: IntroductionCourse OverviewIntroduction to Neural NetworksMulti-Layer Neural Network StructureSection 2: Mathematics of Neural Network TrainingMulti-Layer Neural Network TrainingSection 3: ImplementationTraining ProcessTesting ProcessAnalysis of the Source CodeSection 4: DatasetsTesting with DatasetsSection 5: SummaryQuick ReviewSection 6: ExerciseExercise