Jump to content

  • Log In with Google      Sign In   
  • Create Account


MADE A SIMPLE NEURAL NETWORK, BUT NOT SURE IF I DID IT RIGHT


Old topic!
Guest, the last post of this topic is over 60 days old and at this point you may not reply in this topic. If you wish to continue this conversation start a new topic.

  • You cannot reply to this topic
9 replies to this topic

#1 kazisami   Members   -  Reputation: 458

Like
0Likes
Like

Posted 26 February 2013 - 10:53 PM

A simple single unit adaptive network:

graphic2.gif

The network has 2 inputs, and one output. All are binary. The output
is

1 if W0 *I0 + W1 * I1+ Wb > 0 

0 if W0 *I0 + W1 * I1+ Wb <= 0 

We want it to learn simple OR: output a 1 if either I0 or I1 is 1.

 

 

 

 

 

 

For Solving this problem i have made this-

#include <iostream>
 
struct Newron
{
   int value;
   int weight;
};
 
int main()
{
  Newron input_one, input_two, output;
  int bias = 0;
 
  input_one.weight = 1;
  input_two.weight = 1;
 
  std::cin >> input_one.value;
  std::cin >> input_two.value;
 
  output.value = (input_one.value * input_one.weight) + (input_two.value * input_two.weight) + bias;
 
  if(output.value > 0)
    std::cout << 1 << std::endl;
  else
    std::cout << 0 << std::endl;
 
  return 0;
}

Is it the right way?

If not then how it can be done?

 

Thanks for your help in advance.


Edited by kazisami, 27 February 2013 - 02:30 AM.

To follow the path:

look to the master,

follow the master,

walk with the master,

see through the master,

become the master.

http://kazisami.wordpress.com/


Sponsor:

#2 Cornstalks   Crossbones+   -  Reputation: 6878

Like
0Likes
Like

Posted 26 February 2013 - 11:05 PM

I can't comment, but I'll suggest you a) DON'T MAKE YOUR TITLE LOOK LIKE IT'S SHOUTING, and b) use [ code ][ /code ] (without spaces) tages for code to help with formatting/highlighting.

 

Good luck!


[ I was ninja'd 71 times before I stopped counting a long time ago ] [ f.k.a. MikeTacular ] [ My Blog ] [ SWFer: Gaplessly looped MP3s in your Flash games ]

#3 kazisami   Members   -  Reputation: 458

Like
0Likes
Like

Posted 27 February 2013 - 02:31 AM

I can't comment, but I'll suggest you a) DON'T MAKE YOUR TITLE LOOK LIKE IT'S SHOUTING, and b) use [ code ][ /code ] (without spaces) tages for code to help with formatting/highlighting.

 

Good luck!

Sorry for the title :D And i changed the code formatting, but couldn't be able to change the title.


To follow the path:

look to the master,

follow the master,

walk with the master,

see through the master,

become the master.

http://kazisami.wordpress.com/


#4 Tournicoti   Prime Members   -  Reputation: 679

Like
1Likes
Like

Posted 27 February 2013 - 07:09 AM

Hello

This seems to be a good start for me smile.png

In fact you are precisely describing (wanting ?) Perceptron model

 

This is pseudo-code :

class Neuron
{
	float [] inputs; // (with : true is 1.0f, false is 0.0f)
	float [] weights;

	Constructor(integer nbInputs)
	{
		inputs=new array [nbInputs +1] (+1 is for including the bias). Or getting a reference on an external array.
		weights=new array [nbInputs +1]
		
		fill the weights array with float random values between -1 and 1
		set 1.0f in the position corresponding to the bias in the inputs array(typically, first or last position)
	}
	
	float computeOutput()
	{
		sum=dotProduct(inputs,weights);
		return sum>0.0f;
	}

	void learn(float desiredOutput,float learningRate) // adaptation of the weights
	{
		float output=computeOutput();
		float deltaOutput=desiredOutput-output; (so -1.0f or 0.0f or 1.0f)
		
		for each position in the arrays
		{
			weights[i]+=learningRate*inputs[i]*deltaOutput;
		}
	}

};

 

Hope it makes sense rolleyes.gif

 

for a OR, it should converge with : w1=w2=lambda, and wBias=0. With lambda>0

 

Good luck


Edited by Tournicoti, 02 March 2013 - 09:10 AM.


#5 kazisami   Members   -  Reputation: 458

Like
0Likes
Like

Posted 27 February 2013 - 07:45 AM

Hello

This seems to be a good start for me smile.png

In fact you are precisely describing (wanting ?) Perceptron model

 

This is pseudo-code :

class Neuron
{
	float [] inputs; // (with : true is 1.0f, false is 0.0f)
	float [] weights; //idem

	Constructor(integer nbInputs)
	{
		inputs=new array [nbInputs +1] (+1 is for including the bias). Or getting a reference on an external array.
		weights=new array [nbInputs +1]
		
		fill the weights array with float random values between -1 and 1
		set 1.0f in the position corresponding to the bias in the inputs array(typically, first or last position)
	}
	
	float computeOutput()
	{
		sum=dotProduct(inputs,weights);
		return sum>0.0f;
	}

	void learn(float desiredOutput,float learningRate) // adaptation of the weights
	{
		float output=computeOutput();
		float deltaOutput=desiredOutput-output; (so -1.0f or 0.0f or 1.0f)
		
		for each position in the arrays
		{
			weights[i]+=learningRate*inputs[i]*deltaOutput;
		}
	}

};

 

Hope it makes sense rolleyes.gif

 

for a OR, it should converge with : w1=lambda, w2=lambda, et wBias=0, lambda>0

 

Good luck

 

Thank you very much :D Most of the part is clear to me, but I didn't understood the learningRate argument in the learn() method. Do I have to adjust it so that the network can learn or adjust weight on its own?


To follow the path:

look to the master,

follow the master,

walk with the master,

see through the master,

become the master.

http://kazisami.wordpress.com/


#6 Tournicoti   Prime Members   -  Reputation: 679

Like
1Likes
Like

Posted 27 February 2013 - 08:52 AM

The learning rate is just an user-defined constant, here. It's usually a value between 0 and 1.

It's like defining the 'step' of the adaptation.

 

I would suggest to try low values first  (0.2 ? even less ?) because inputs[i]*deltaOutput is here a huge value : -1 or 0 or 1 !

 

Afterwards, the goal is to maximize the learning rate so that the learning process is quicker but still accurate enough for the wanted approximation.

 

Hope I'm still clear smile.png (sorry for my english, I'm getting tiredph34r.png )

 

Bye


Edited by Tournicoti, 27 February 2013 - 10:26 AM.


#7 kazisami   Members   -  Reputation: 458

Like
1Likes
Like

Posted 27 February 2013 - 09:59 AM

Don't worry, your english is as awesome as your explanation :D I am getting a hold of this, but I need to experiment a lot before I can understand it clearly. But you answered my question and that's enough for starting experiment without any confusion.

 

Thanks a lot for your help :D


To follow the path:

look to the master,

follow the master,

walk with the master,

see through the master,

become the master.

http://kazisami.wordpress.com/


#8 Tournicoti   Prime Members   -  Reputation: 679

Like
0Likes
Like

Posted 27 February 2013 - 10:25 AM

Very glad I could help you !


Edited by Tournicoti, 27 February 2013 - 10:38 AM.


#9 Tournicoti   Prime Members   -  Reputation: 679

Like
2Likes
Like

Posted 28 February 2013 - 06:56 PM

I would like to add another little thing :

 

What I described is the Perceptron as it was designed by Frank Rosenblatt (original version)

However there's another (very slightly different !) version in which -1 and 1 are used instead of 0 and 1 to encode booleans.

 

 

In term of learning efficiency it's better because  :

  • with 0 and 1, the weights will evolve only when deltaOutput is not zero and input is not zero.
  • with -1 and 1, the weights will always evolves when deltaOutput is not zero.

 

And this is 'nothing' to change :

  • change input encoding (so no more 0 and 1, but -1 and 1)
  • change the activation function :  sum>0.0f ? 1.0f : -1.0f

Bye smile.png



#10 kazisami   Members   -  Reputation: 458

Like
0Likes
Like

Posted 01 March 2013 - 01:35 AM

Thanks again for the help. You know what, I was going to ask you the same thing. I was looking for some other neural networks, then I came across Hopfield network and there is a step when we need to convert the boolean(1 and 0) to 1 and -1. Then I was thinking if this could be done with Perceptron too. And before I could ask, you answered it :)


Edited by kazisami, 01 March 2013 - 01:36 AM.

To follow the path:

look to the master,

follow the master,

walk with the master,

see through the master,

become the master.

http://kazisami.wordpress.com/





Old topic!
Guest, the last post of this topic is over 60 days old and at this point you may not reply in this topic. If you wish to continue this conversation start a new topic.



PARTNERS