Search All of the Math Forum:

Views expressed in these public forums are not endorsed by NCTM or The Math Forum.

Notice: We are no longer accepting new posts, but the forums will continue to be readable.

Topic: Neural Networks weights and bias help
Replies: 18   Last Post: Jan 22, 2016 9:11 AM

 Messages: [ Previous | Next ]
 hasan batuk Posts: 4 Registered: 8/13/10
Neural Networks weights and bias help
Posted: Aug 13, 2010 10:47 AM

Hi, i am trying to learn NN toolbox. I tried to creat a networks that multiply the number by 3 and gives as output. For simplicity, i made the transfer function also linear. It works well but i tried to reach the same result by using the bias and weight values.
x -> input
y-> output

a= [ (w1*x + b1) * w2 ]+b2

but it ends up with same as the input value. I am really confused about it. it looks very simple but i couldnt find what i miss. Thanks for your time. the code is below

P=[1:4:200]; % training set
T=P*3; % target set

net=newff(P,T,1);
net.layers{1}.transferFcn = 'purelin'; % making transfer func. as linear

net=train(net,P,T);

y=sim(net,101) % giving a number say 101 as an input to system and taking 303 as output as expected.

% trying to reach same result by using weight and bias values. it ends up with 101, not 303.

a1=(net.iw{1,1}*101)+net.b{1}; % output of first layer

a2=(net.lw{2,1}*a1)+net.b{2} % output of second layer

Date Subject Author
8/13/10 hasan batuk
8/13/10 Greg Heath
8/15/10 hasan batuk
8/15/10 Greg Heath
8/16/10 hasan batuk
8/17/10 Greg Heath
8/17/10 hasan batuk
8/17/10 Greg Heath
12/12/12 Renan
12/13/12 Greg Heath
12/20/12 Murugan Solaiyappan
1/20/16 Vikas
1/20/16 Greg Heath
1/21/16 Vikas
1/22/16 Greg Heath
1/22/16 Vikas
1/22/16 Vikas
1/22/16 Vikas
1/22/16 Greg Heath