Introduction to Artificial Neural networks (4)--aforge.net

1 Introduction

In this article, we will introduce a framework aforge using C #, which allows you to easily manipulate artificial networks, computer vision, machine learning, image processing, genetic algorithms, etc.

Introduction of 2 neural network design part framework

Here, I want to emphasize: This piece of code is very beautiful, a code such as poetic beauty, let me charmed.

This piece of code is in the Aforge.neuro name space.

This library file consists of 6 main parts:

Neuron-an abstract base class for all neurons (neurons) that encapsulates some of the basic elements common to all Neuron: weights, output values, and input values. Other neuron are derived from this foundation.

Layer-Represents a collection of neurons. This abstract base class encapsulates the commonality of the layer (Layer).

Network-represents a neural network, a collection of neuron ' s layers. This abstract base class provides the commonality of the network. Other network are derived from this foundation.

Iactivationfunction-Interface for activating functions (activation function). All activation functions are derived from this interface

Iunsupervisedlearning-the interface of the tutorial-free learning (unsupervised learning) algorithm-This type of learning system provides input only in the learning process and does not provide desired output for that input. The goal of the system is to continually find better solutions.

Isupervisedlearning-an interface to the tutorial learning (supervised learning) algorithm-This type of learning system provides input and expected output for the input during the learning process. The goal of the system is to continually revise the network through actual output and expected output.

The relationships of these classes can be represented in the following illustration:

This file contains the following 2 neural network systems:

Activation network

Distance Network

The following 5 learning algorithms are also available to solve different problems:

Perceptron Learning

Delta Rule Learning

Back propagation Learning

SOM Learning

Elastic Network Learning