OpenNN C++ Tutorials

Getting started:

Start working with openNN with the following tutorials

Building OpenNN

Learn how to build the OpenNN library on any system using our project files for Qt creator. If working with another compiler is needed, you will learn how to create a project for it.

OpenNN in 6 steps

This tutorial shows the principal ingredients to build a neural network model in a few steps using OpenNN.

The software model of OpenNN

Discover the software model of OpenNN, carried out in the Unified Modeling Language (UML), which is used to specify, visualize, construct, and document the artefacts of a software system.

Machine learning examples:

Discover examples using our software OpenNN Neural Networks

Approximation:
Airfoil self-noise prediction

The fundamental goal of this example is to predict the noise generated by an aircraft's airfoil blades.

Classification:
Breast cancer diagnosis

This example aims to assess whether a lump in a breast could be malignant (cancerous) or benign (non-cancerous) from digitized images of a fine-needle aspiration biopsy.

Forecasting:
Airline passengers estimation

In this example, we will forecast airline passengers number from past years' data.

Text Classification:
Amazon reviews classification

The main goal of this example is to classify amazon customer reviews into positive and negative.

Main classes:

Learn how to use the main classes of OpenNN

Vector, Matrix and Tensor templates

In this tutorial, we will learn about the Vector, Matrix, and Tensor templates and how OpenNN allows you to easily work with them.

The data set class

The data set contains the information needed to construct the predictive model. In this tutorial, we will see how to use that concept within OpenNN.

The neural network class

Discover the class of neural networks implemented in OpenNN, based on the multilayer perceptron. That model is extended here to contain scaling, unscaling, bounding, probabilistic, and conditions layers.

The training strategy class

The procedure used to carry out the learning process in a neural network is called the training strategy. In this tutorial, you will learn about how to use a training strategy in OpenNN.

The model selection class

To obtain the best model, we have to optimize the architecture of the neural network. This tutorial shows the different types of model optimization and the algorithms contained in OpenNN.

The testing analysis class

The purpose of testing is to compare the outputs from the neural network against targets in an independent testing set. Here you will learn how to test the quality of a model for different types of problems.