Jump to content

Recommended Posts

Hey there!


I'm trying to rebuild a python script in AU3, i've been wandering and trying to figure out how i could do it


The .py script is this:


import numpy as np

def nonlin(x,deriv=False):
        return x*(1-x)

    return 1/(1+np.exp(-x))
X = np.array([[0,0,1],
y = np.array([[0],


# randomly initialize our weights with mean 0
syn0 = 2*np.random.random((3,4)) - 1
syn1 = 2*np.random.random((4,1)) - 1

for j in xrange(60000):

    # Feed forward through layers 0, 1, and 2
    l0 = X
    l1 = nonlin(np.dot(l0,syn0))
    l2 = nonlin(np.dot(l1,syn1))

    # how much did we miss the target value?
    l2_error = y - l2
    if (j% 10000) == 0:
        print "Error:" + str(np.mean(np.abs(l2_error)))
    # in what direction is the target value?
    # were we really sure? if so, don't change too much.
    l2_delta = l2_error*nonlin(l2,deriv=True)

    # how much did each l1 value contribute to the l2 error (according to the weights)?
    l1_error = l2_delta.dot(syn1.T)
    # in what direction is the target l1?
    # were we really sure? if so, don't change too much.
    l1_delta = l1_error * nonlin(l1,deriv=True)

    syn1 += l1.T.dot(l2_delta)
    syn0 += l0.T.dot(l1_delta)

So far, i got this:


    $NN_Ins = FileOpen($Netfile)
    $IFRead = FileReadLine($NN_Ins, 1)
    $NRFlags = StringSplit($IFRead, '/')
    $NFlags[3] = [$NRFlags[1], _
                    $NRFlags[2], _
                        $NRFlags[3] ]
    Global $DSI[4][3] = [[0,0,1], [0,1,1], [1,0,1], [1,1,1]]
    Global $DSO[4] = [0, 1, 1, 0]
    Global $DTV = Vector()
    $DTV.Init($DSI, $DSO)
    $syn0 = 2*(Random(3,4) - 1)
    $syn1 = 2*(Random(1, 4) - 1)
    For $x In $DSI
        For $y in $DSO
        $l1 = 1/(1+Exp($DTV.Dot($x, $syn0))
        $l2 = 1/(1+Exp($DTV.Dot($l1, $syn1))
        $d0 = ($y - $l2)*($l2*(1-$l2))
        $d1 ; i got lost
    Func Vector()
    Local $this = _AutoItObject_Create()
    _AutoItObject_AddMethod($this, "Dot", "Vector_DotProduct")
    Return $this
EndFunc ;==>Vector
Func Vector_DotProduct($this, $vector1 = '', $vector2 = '')
    Switch IsArray($vector1) And IsArray($vector2)
        Case 1
            Switch UBound($vector1) >= 3 And UBound($vector1) >= 3
                Case 1
                    Local $DotProduct[3]
                Case 0

        Case 0
            Return SetError(1, 0, -1)
EndFunc ;==>Vector_DotProduct

The purpose of the main script is simulating an artificial neural network with algebra.

I'm lost on the part where i must declare $l1 and $l2 variables, the value is supposed to be the dotproduct of 2 variables, but i don't know how i can do that (I'm also horrible at algebra:()

I know about the "We help you to fix ur code, not code for you", but, honestly, i'm lost - i'm not good at python, neither on AutoIt, excuse me for it.


Any help is really appreciated


Thanks in advance

Link to post
Share on other sites

Look here:

and this thread:


This wonderful site allows debugging and testing regular expressions (many flavors available). An absolute must have in your bookmarks.
Another excellent RegExp tutorial. Don't forget downloading your copy of up-to-date pcretest.exe and pcregrep.exe here
RegExp tutorial: enough to get started
PCRE v8.33 regexp documentation latest available release and currently implemented in AutoIt beta.

SQLitespeed is another feature-rich premier SQLite manager (includes import/export). Well worth a try.
SQLite Expert (freeware Personal Edition or payware Pro version) is a very useful SQLite database manager.
An excellent eBook covering almost every aspect of SQLite3: a must-read for anyone doing serious work.
SQL tutorial (covers "generic" SQL, but most of it applies to SQLite as well)
A work-in-progress SQLite3 tutorial. Don't miss other LxyzTHW pages!
SQLite official website with full documentation (may be newer than the SQLite library that comes standard with AutoIt)

Link to post
Share on other sites

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!

Register a new account

Sign in

Already have an account? Sign in here.

Sign In Now
  • Recently Browsing   0 members

    No registered users viewing this page.

  • Create New...