MESSAGE
| DATE | 2017-03-29 |
| FROM | Ruben Safir
|
| SUBJECT | Subject: [Learn] perseptors
|
From learn-bounces-at-nylxs.com Wed Mar 29 22:50:35 2017
Return-Path:
X-Original-To: archive-at-mrbrklyn.com
Delivered-To: archive-at-mrbrklyn.com
Received: from www.mrbrklyn.com (www.mrbrklyn.com [96.57.23.82])
by mrbrklyn.com (Postfix) with ESMTP id 0838C161312;
Wed, 29 Mar 2017 22:50:35 -0400 (EDT)
X-Original-To: learn-at-nylxs.com
Delivered-To: learn-at-nylxs.com
Received: from [10.0.0.62] (flatbush.mrbrklyn.com [10.0.0.62])
by mrbrklyn.com (Postfix) with ESMTP id A4066160E77
for ; Wed, 29 Mar 2017 22:50:31 -0400 (EDT)
From: Ruben Safir
To: "learn-at-nylxs.com"
Message-ID: <563a5295-9353-94b0-104f-0c9a23d7c2f6-at-mrbrklyn.com>
Date: Wed, 29 Mar 2017 22:50:31 -0400
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:45.0) Gecko/20100101
Thunderbird/45.8.0
MIME-Version: 1.0
Content-Type: multipart/mixed; boundary="------------A7A24B8B06275A636C512F1E"
Subject: [Learn] perseptors
X-BeenThere: learn-at-nylxs.com
X-Mailman-Version: 2.1.17
Precedence: list
List-Id:
List-Unsubscribe: ,
List-Archive:
List-Post:
List-Help:
List-Subscribe: ,
Errors-To: learn-bounces-at-nylxs.com
Sender: "Learn"
This is a multi-part message in MIME format.
--------------A7A24B8B06275A636C512F1E
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: 7bit
base gig
--
So many immigrant groups have swept through our town
that Brooklyn, like Atlantis, reaches mythological
proportions in the mind of the world - RI Safir 1998
http://www.mrbrklyn.com
DRM is THEFT - We are the STAKEHOLDERS - RI Safir 2002
http://www.nylxs.com - Leadership Development in Free Software
http://www2.mrbrklyn.com/resources - Unpublished Archive
http://www.coinhangout.com - coins!
http://www.brooklyn-living.com
Being so tracked is for FARM ANIMALS and and extermination camps,
but incompatible with living as a free human being. -RI Safir 2013
--------------A7A24B8B06275A636C512F1E
Content-Type: text/x-c++src;
name="learn.cpp"
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
filename="learn.cpp"
/*
* =====================================================================================
*
* Filename: learn.cpp
*
* Description: Learn with a Neuronet and Perceptrons
*
* Version: 1.0
* Created: 03/29/2017 04:14:13 PM
* Revision: none
* Compiler: gcc
*
* Author: Ruben Safir (mn), ruben-at-mrbrklyn.com
* Company: NYLXS Inc
*
* =====================================================================================
*/
#include "perceptron.h"
const float LEARN_RATE = 0.2;
const int PRECISION = 3;
const int NUMWIDTH = PRECISION + 3;
void tt(std::vector truth_table ){
std::cout << std::endl << "__Truth Table__" << std::endl;
for(auto x : truth_table)
{
std::cout << x << "\t";
}
std::cout << std::endl;
}
int main (int argc, char ** argv )
{
std::vector * sensor_inputs[4] = {
new std::vector {0,0},
new std::vector {0,1},
new std::vector {1,0},
new std::vector{1,1}
};
std::vector weight_inputs = { 0.4, 0.4, 0.0 };
std::vector truth_table(4);
for(int i = 0; i<4; i++){
network::Perceptron p_and (*sensor_inputs[i],weight_inputs, 0.5);
std::cout << "AND sum =>" << p_and.get_sum() << std::endl << std::endl;
std::cout << "AND threshold =>" << p_and.get_threshold() << std::endl;
std::cout << "AND Functor =>" << p_and.functor() << std::endl << std::endl;
truth_table[i] = p_and.functor();
}
tt(truth_table);
weight_inputs[0] = 0.6;
weight_inputs[1] = 0.6;
weight_inputs[2] = 0.0;
for(int i = 0; i<4; i++){
network::Perceptron p_or (*sensor_inputs[i],weight_inputs, 0.5);
std::cout << "XOR sum =>" << p_or.get_sum() << std::endl;
std::cout << "XOR threshold =>" << p_or.get_threshold() << std::endl;
std::cout << "XOR Functor =>" << p_or.functor() << std::endl;
truth_table[i] = p_or.functor();
}
tt(truth_table);
weight_inputs[0] = -0.4;
weight_inputs[1] = -0.4;
weight_inputs[2] = 0.0;
for(int i = 0; i<4; i++){
network::Perceptron p_or (*sensor_inputs[i],weight_inputs, -0.5);
std::cout << "NAND sum =>" << p_or.get_sum() << std::endl;
std::cout << "NAND threshold =>" << p_or.get_threshold() << std::endl;
std::cout << "NAND Functor =>" << p_or.functor() << std::endl;
truth_table[i] = p_or.functor();
}
tt(truth_table);
return 1;
}
--------------A7A24B8B06275A636C512F1E
Content-Type: text/x-chdr;
name="perceptron.h"
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
filename="perceptron.h"
/*
* =====================================================================================
*
* Filename: perceptron.h
*
* Description: Basic Unit for AI machine learning
*
* Version: 1.0
* Created Mon Mar 27 22:33:19 EDT 2017
* Revision: none
* Compiler: gcc
*
* Author: Ruben Safir (mn), ruben-at-mrbrklyn.com
* Company: NYLXS Inc - LIU Thesis
*
* =====================================================================================
*/
#ifndef PERCEPTRON_H
#define PERCEPTRON_H
#include
#include
#include
namespace network {
/*
* =====================================================================================
* Class: Perceptron
* Description: This class describes a single node and its data
* =====================================================================================
*/
template < class T, class W >
class Perceptron
{
public:
/* ==================== LIFECYCLE ======================================= */
Perceptron ( std::vector s1, std::vector w1, float thresh ): sensors{s1}, weights{w1}, threshold{thresh} {
sensors.push_back(1);
weighted_sum();
}; /* constructor */
/* ==================== ACCESSORS ======================================= */
W get_sum()
{
// std::cout << "Called get sum" << std::endl;
return sum;
};
float get_threshold()
{
return threshold;
};
/* ==================== MUTATORS ======================================= */
int functor()
{
if(sum < get_threshold())
{
return 0;
}else{
return 1;
}
}
/* ==================== OPERATORS ======================================= */
/* ==================== DATA MEMBERS ======================================= */
T data;
protected:
private:
std::vector sensors;
std::vector weights;
float threshold;
float sum = 0;
float weighted_sum()
{
if( sensors.size() != weights.size() )
{
std::cerr << __LINE__ << " You broke my perceptron by failing to give a weight for the bias";
exit(1);
}
for (int i = 0; i < static_cast ( sensors.size()) ; i++)
{
std::cout << "sensor =>" << sensors[i] << std::endl;
std::cout << "weight =>" << weights[i] << std::endl;
sum += weights[i] * sensors[i];
// std::cout << "sum =>" << sum << std::endl;
// std::cout << "get sum =>" << get_sum() << std::endl;
};
return sum;
};
}; /* ---------- end of template class Perceptron ---------- */
}//close of namespace network
#endif
--------------A7A24B8B06275A636C512F1E
Content-Type: text/x-c++src;
name="perceptron.cpp"
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
filename="perceptron.cpp"
#include "perceptron.h"
#include
--------------A7A24B8B06275A636C512F1E
Content-Type: text/plain; charset=UTF-8;
name="makefile"
Content-Transfer-Encoding: base64
Content-Disposition: attachment;
filename="makefile"
WFg6PWdjYwpDWFhGTEFHUzo9LVdhbGwgLWdnZGIgLXBnIApMREZMQUdTOj0gLXBnIC1wdGhy
ZWFkCgpsZWFybjogcGVyY2VwdHJvbi5vIGxlYXJuLm8KCSQoQ1hYKSAkKENYWEZMQUdTKSAk
KExERkxBR1MpIC1vIGxlYXJuLmV4ZSBwZXJjZXB0cm9uLm8gbGVhcm4ubwoKcGVyY2VwdHJv
bjogcGVyY2VwdHJvbi5jcHAgcGVyY2VwdHJvbi5oCgkkKENYWCkgJChDWFhGTEFHUykgJChM
REZMQUdTKSAtYyBwZXJjZXB0cm9uLmNwcAoKbm9kZXM6IGxlYXJuLmNwcCBsZWFybi5oCgkk
KENYWCkgJChDWFhGTEFHUykgJChMREZMQUdTKSAtYyBsZWFybi5jcHAgCgppbmNsdWRlIG1h
a2UuZGVwcwptYWtlLmRlcHM6ICouY3BwOyAke0NYWH0gJHtDWFhGTEFHU30gLU0gKi5jcHAg
PiRACgo=
--------------A7A24B8B06275A636C512F1E
Content-Type: text/plain; charset="us-ascii"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
Content-Disposition: inline
_______________________________________________
Learn mailing list
Learn-at-nylxs.com
http://lists.mrbrklyn.com/mailman/listinfo/learn
--------------A7A24B8B06275A636C512F1E--
|
|
