Artificial intelligence - Class TPerceptron

Re: Artificial intelligence - Class TPerceptron

Postby Enrico Maria Giordano » Fri May 19, 2017 8:04 am

rhlawek wrote:I've been looking for some old source code to prove it to myself but this looks very similar to what I was taught as Predictor/Corrector methods back in the mid-80s


Yes, it's a very old concept. But still interesting.

EMG
User avatar
Enrico Maria Giordano
 
Posts: 8243
Joined: Thu Oct 06, 2005 8:17 pm
Location: Roma - Italia

Re: Artificial intelligence - Class TPerceptron

Postby Antonio Linares » Fri May 19, 2017 10:35 am

Pedro Domingos name them "learners": software that can "learn" from data.

The simplest way of learning from data is comparing two bytes. How ? Substracting them: A zero means they are equal, different from zero means they are different.
The difference between them is the "error". To correct the error, we modify a "weight" . Its amazing that from that simple concept, all what can be built. In the same way all our software technology comes from a bit, being zero or one.

The perceptron mimics (in a very simple way) the behavior of a brain neuron. The neuron receives several inputs, each one has a weight (stored at the neuron) and the sum of all those inputs times their weights may fire or not an output.

Backpropagation helps to fine tune those weights, and finally the perceptron "adjusts" itself to the right weight for each input to produce the expected output.

AI is already everywhere and will change very much our lives and the way software is developed :-)
regards, saludos

Antonio Linares
www.fivetechsoft.com
User avatar
Antonio Linares
Site Admin
 
Posts: 41206
Joined: Thu Oct 06, 2005 5:47 pm
Location: Spain

Re: Artificial intelligence - Class TPerceptron

Postby Antonio Linares » Tue May 23, 2017 8:49 am

Image
regards, saludos

Antonio Linares
www.fivetechsoft.com
User avatar
Antonio Linares
Site Admin
 
Posts: 41206
Joined: Thu Oct 06, 2005 5:47 pm
Location: Spain

Re: Artificial intelligence - Class TPerceptron

Postby Antonio Linares » Tue May 23, 2017 9:33 am

Image

Perceptrón Multicapa
regards, saludos

Antonio Linares
www.fivetechsoft.com
User avatar
Antonio Linares
Site Admin
 
Posts: 41206
Joined: Thu Oct 06, 2005 5:47 pm
Location: Spain

Re: Artificial intelligence - Class TPerceptron

Postby Antonio Linares » Fri May 26, 2017 6:37 pm

regards, saludos

Antonio Linares
www.fivetechsoft.com
User avatar
Antonio Linares
Site Admin
 
Posts: 41206
Joined: Thu Oct 06, 2005 5:47 pm
Location: Spain

Re: Artificial intelligence - Class TPerceptron

Postby Antonio Linares » Fri May 26, 2017 8:05 pm

David Miller C++ code ported to Harbour:

viewtopic.php?p=202115#p202115

Don't miss to try your first neural network :-)
regards, saludos

Antonio Linares
www.fivetechsoft.com
User avatar
Antonio Linares
Site Admin
 
Posts: 41206
Joined: Thu Oct 06, 2005 5:47 pm
Location: Spain

Re: Artificial intelligence - Class TPerceptron

Postby Antonio Linares » Thu Jun 01, 2017 4:12 pm

Inspecting the neural network:

Code: Select all  Expand view
#include "FiveWin.ch"

function Main()

   local oNet := TNet():New( { 1, 2, 1 } ), n
   local x

   while oNet:nRecentAverageError < 0.95
      oNet:FeedForward( { x := nRandom( 1000 ) } )
      oNet:Backprop( { If( x % 5 == 0, 5, 1 ) } )
   end  

   oNet:FeedForward( { 15 } )
   
   XBROWSER ArrTranspose( { "Layer 1 1st neuron" + CRLF + "Input:" + Str( oNet:aLayers[ 1 ][ 1 ]:nOutput ) + ;
                                                   CRLF + "Weigth 1:" + Str( oNet:aLayers[ 1 ][ 1 ]:aWeights[ 1 ], 4, 2 ), ;
                            { "Layer 2, 1st neuron" + CRLF + "Weigth 1: " + Str( oNet:aLayers[ 2 ][ 1 ]:aWeights[ 1 ] ) + ;
                                                      CRLF + "Output: " + Str( oNet:aLayers[ 2 ][ 1 ]:nOutput ),;
                            "Layer 2, 2nd neuron" + CRLF + "Weight 1: " + Str( oNet:aLayers[ 2 ][ 2 ]:aWeights[ 1 ] ) + ;
                                                    CRLF + "Output: " + Str( oNet:aLayers[ 2 ][ 2 ]:nOutput ) },;
                            "Layer 3 1st neuron" + CRLF + "Weigth 1: " + Str( oNet:aLayers[ 3 ][ 1 ]:aWeights[ 1 ] ) + ;
                                                   CRLF + "Weigth 2: " + Str( oNet:aLayers[ 3 ][ 1 ]:aWeights[ 2 ] ) + ;
                                                   CRLF + "Output: " + Str( oNet:aLayers[ 2 ][ 2 ]:nOutput ) } ) ;
      SETUP ( oBrw:nDataLines := 4,;
              oBrw:aCols[ 1 ]:nWidth := 180,;
              oBrw:aCols[ 2 ]:nWidth := 180,;
              oBrw:aCols[ 3 ]:nWidth := 180,;
              oBrw:nMarqueeStyle := 3 )                      
   
return nil


Image
regards, saludos

Antonio Linares
www.fivetechsoft.com
User avatar
Antonio Linares
Site Admin
 
Posts: 41206
Joined: Thu Oct 06, 2005 5:47 pm
Location: Spain

Re: Artificial intelligence - Class TPerceptron

Postby Antonio Linares » Sat Jun 24, 2017 5:51 am

Teaching a perceptron to multiply a number by 2:

Code: Select all  Expand view
#include "FiveWin.ch"

function Main()

   local oNeuron := TPerceptron():New( 1 )
   local n, nValue

   for n = 1 to 50
      oNeuron:Learn( { nValue := nRandom( 1000 ) }, ExpectedResult( nValue ) )
   next

   MsgInfo( oNeuron:aWeights[ 1 ] )
   
   MsgInfo( oNeuron:Calculate( { 5 } ) )

return nil  

function ExpectedResult( nValue )

return nValue * 2

CLASS TPerceptron

   DATA aWeights

   METHOD New( nInputs )

   METHOD Learn( aInputs, nExpectedResult )

   METHOD Calculate( aInputs )

ENDCLASS

METHOD New( nInputs ) CLASS TPerceptron

   local n

   ::aWeights = Array( nInputs )

   for n = 1 to nInputs
      ::aWeights[ n ] = 0
   next

return Self

METHOD Learn( aInputs, nExpectedResult ) CLASS TPerceptron

   local nSum := ::Calculate( aInputs )

   if nSum < nExpectedResult
      ::aWeights[ 1 ] += 0.1
   endif

   if nSum > nExpectedResult
      ::aWeights[ 1 ] -= 0.1
   endif

return nil        

METHOD Calculate( aInputs ) CLASS TPerceptron

   local n, nSum := 0

   for n = 1 to Len( aInputs )
      nSum += aInputs[ n ] * ::aWeights[ n ]
   next

return nSum
regards, saludos

Antonio Linares
www.fivetechsoft.com
User avatar
Antonio Linares
Site Admin
 
Posts: 41206
Joined: Thu Oct 06, 2005 5:47 pm
Location: Spain

Re: Artificial intelligence - Class TPerceptron

Postby Silvio.Falconi » Wed Jun 28, 2017 4:07 pm

Since from 1991/1992 ( fw for clipper Rel. 14.4 - Momos)
I use : FiveWin for Harbour November 2023 - January 2024 - Harbour 3.2.0dev (harbour_bcc770_32_20240309) - Bcc7.70 - xMate ver. 1.15.3 - PellesC - mail: silvio[dot]falconi[at]gmail[dot]com
User avatar
Silvio.Falconi
 
Posts: 6716
Joined: Thu Oct 18, 2012 7:17 pm

Re: Artificial intelligence - Class TPerceptron

Postby Antonio Linares » Mon Jul 17, 2017 3:47 am

regards, saludos

Antonio Linares
www.fivetechsoft.com
User avatar
Antonio Linares
Site Admin
 
Posts: 41206
Joined: Thu Oct 06, 2005 5:47 pm
Location: Spain


Re: Artificial intelligence - Class TPerceptron

Postby Antonio Linares » Sun Jul 23, 2017 9:11 am

Scaled value: ( Input Value - Minimum ) / ( Maximum - Minimum )

Descaled value (Input Value): ( Scaled value * ( Maximum - Minimum ) ) + Minimum
regards, saludos

Antonio Linares
www.fivetechsoft.com
User avatar
Antonio Linares
Site Admin
 
Posts: 41206
Joined: Thu Oct 06, 2005 5:47 pm
Location: Spain

Re: Artificial intelligence - Class TPerceptron

Postby Antonio Linares » Sun Jul 23, 2017 9:52 am

Test of scaling and descaling values:

Scaling: ( value - minimum ) / ( Maximum - Minimum )

0 --> ( 0 - 0 ) / ( 9 - 0 ) --> 0
1 --> ( 1 - 0 ) / ( 9 - 0 ) --> 0.111
2 --> ( 2 - 0 ) / ( 9 - 0 ) --> 0.222
3 --> ( 3 - 0 ) / ( 9 - 0 ) --> 0.333
4 --> ( 4 - 0 ) / ( 9 - 0 ) --> 0.444
5 --> ( 5 - 0 ) / ( 9 - 0 ) --> 0.555
6 --> ( 6 - 0 ) / ( 9 - 0 ) --> 0.666
7 --> ( 7 - 0 ) / ( 9 - 0 ) --> 0.777
8 --> ( 8 - 0 ) / ( 9 - 0 ) --> 0.888
9 --> ( 9 - 0 ) / ( 9 - 0 ) --> 1
regards, saludos

Antonio Linares
www.fivetechsoft.com
User avatar
Antonio Linares
Site Admin
 
Posts: 41206
Joined: Thu Oct 06, 2005 5:47 pm
Location: Spain

Re: Artificial intelligence - Class TPerceptron

Postby Antonio Linares » Fri Aug 04, 2017 5:35 am

In TensorFlow we have the Softmax function which transforms the output of each unit to a value between 0 and 1, and makes the sum of all units equals 1. It will tell us the probability of each category

https://medium.com/@Synced/big-picture-machine-learning-classifying-text-with-neural-networks-and-tensorflow-da3358625601
regards, saludos

Antonio Linares
www.fivetechsoft.com
User avatar
Antonio Linares
Site Admin
 
Posts: 41206
Joined: Thu Oct 06, 2005 5:47 pm
Location: Spain

Re: Artificial intelligence - Class TPerceptron

Postby Carles » Sat Sep 02, 2017 7:23 pm

Hola !

Articulo interesante que ayuda a entrar en este mundillo... https://blogs.elconfidencial.com/tecnol ... n_1437007/

Saludetes.
Salutacions, saludos, regards

"...programar es fácil, hacer programas es difícil..."

UT Page -> https://carles9000.github.io/
Forum UT -> https://discord.gg/bq8a9yGMWh
Skype -> https://join.skype.com/cnzQg3Kr1dnk
User avatar
Carles
 
Posts: 1082
Joined: Fri Feb 10, 2006 2:34 pm
Location: Barcelona

Previous

Return to AI Introduction (Harbour code and samples)

Who is online

Users browsing this forum: No registered users and 1 guest