Page 2 of 2
Re: Artificial intelligence - Class TPerceptron
Posted: Fri May 19, 2017 8:04 am
by Enrico Maria Giordano
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
Re: Artificial intelligence - Class TPerceptron
Posted: Fri May 19, 2017 10:35 am
by Antonio Linares
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
Re: Artificial intelligence - Class TPerceptron
Posted: Tue May 23, 2017 8:49 am
by Antonio Linares
Re: Artificial intelligence - Class TPerceptron
Posted: Tue May 23, 2017 9:33 am
by Antonio Linares
Perceptrón
Multicapa
Re: Artificial intelligence - Class TPerceptron
Posted: Fri May 26, 2017 6:37 pm
by Antonio Linares
Re: Artificial intelligence - Class TPerceptron
Posted: Fri May 26, 2017 8:05 pm
by Antonio Linares
David Miller C++ code ported to Harbour:
viewtopic.php?p=202115#p202115Don't miss to try your first neural network
Re: Artificial intelligence - Class TPerceptron
Posted: Thu Jun 01, 2017 4:12 pm
by Antonio Linares
Inspecting the neural network:
Code: Select all | Expand
#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
Re: Artificial intelligence - Class TPerceptron
Posted: Sat Jun 24, 2017 5:51 am
by Antonio Linares
Teaching a perceptron to multiply a number by 2:Code: Select all | Expand
#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
Re: Artificial intelligence - Class TPerceptron
Posted: Wed Jun 28, 2017 4:07 pm
by Silvio.Falconi
Re: Artificial intelligence - Class TPerceptron
Posted: Mon Jul 17, 2017 3:47 am
by Antonio Linares
Re: Artificial intelligence - Class TPerceptron
Posted: Fri Jul 21, 2017 3:55 am
by Antonio Linares
Re: Artificial intelligence - Class TPerceptron
Posted: Sun Jul 23, 2017 9:11 am
by Antonio Linares
Scaled value: ( Input Value - Minimum ) / ( Maximum - Minimum )
Descaled value (Input Value): ( Scaled value * ( Maximum - Minimum ) ) + Minimum
Re: Artificial intelligence - Class TPerceptron
Posted: Sun Jul 23, 2017 9:52 am
by Antonio Linares
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
Re: Artificial intelligence - Class TPerceptron
Posted: Fri Aug 04, 2017 5:35 am
by Antonio Linares
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
Re: Artificial intelligence - Class TPerceptron
Posted: Sat Sep 02, 2017 7:23 pm
by Carles
Hola !
Articulo interesante que ayuda a entrar en este mundillo...
https://blogs.elconfidencial.com/tecnol ... n_1437007/Saludetes.
