Click here to Skip to main content
15,881,882 members
Articles / Programming Languages / UML

Designing And Implementing A Neural Network Library For Handwriting Detection, Image Analysis etc.- The BrainNet Library - Full Code, Simplified Theory, Full Illustration, And Examples

Rate me:
Please Sign up or sign in to vote.
4.76/5 (97 votes)
21 Oct 2009CPOL26 min read 372.8K   7.8K   356  
This article will explain the actual concepts and implementation of Backward Propagation Neural Networks very easily - see project code and samples, like a simple pattern detector, a hand writing detection pad, an xml based neural network processing language etc in the source zip.
'------------------------------------------------------------------
' License Notice:
'------------------------------------------------------------------
' All Rights Reserved - Anoop Madhusudanan, 
' Mail: amazedsaint@gmail.com
' Website: http://amazedsaint.blogspot.com

' See my articles about BrainNet at 
' http://amazedsaint-articles.blogspot.com for details
'
' You can use this code (or part of it), for non 
' commercial and academic uses, as long as 
'   - You are keeping this notice along with it
'   - You are not making any profit out of this
'------------------------------------------------------------------

'''<summary>This is a hashtable to keep track of all neurons connected to a neuron,
''' and its related weights</summary>
Public Class NeuronConnections
    Inherits Hashtable


    '''<summary>This class wraps a weight value holded by a neuron </summary>
    Private Class WeightMapping
        Public Weight As Single
        Public Sub New(ByVal weight As Single)
            Me.Weight = weight
        End Sub
    End Class

    Public Shadows Function Add(ByRef input As INeuron, ByVal weight As Single) As INeuron
        MyBase.Add(input, New WeightMapping(weight))
        Add = input
    End Function

    Public Shadows Function Add(ByRef input As INeuron) As INeuron
        MyBase.Add(input, New WeightMapping(Utility.Rand))
        Add = input
    End Function


    Public Shadows Sub Remove(ByVal obj As INeuron)
        MyBase.Remove(obj)
    End Sub

    Public Function Neurons() As ICollection
        Return MyBase.Keys
    End Function


    Default Public Shadows Property Weight(ByVal obj As INeuron) As Single
        Get
            Return CType(MyBase.Item(obj), WeightMapping).Weight
        End Get

        Set(ByVal val As Single)
            CType(MyBase.Item(obj), WeightMapping).Weight = val
        End Set

    End Property

End Class

By viewing downloads associated with this article you agree to the Terms of Service and the article's licence.

If a file you wish to view isn't highlighted, and is a text file (not binary), please let us know and we'll add colourisation support for it.

License

This article, along with any associated source code and files, is licensed under The Code Project Open License (CPOL)


Written By
Architect
India India
Architect, Developer, Speaker | Wannabe GUT inventor & Data Scientist | Microsoft MVP in C#

Comments and Discussions