Databases
StackOverflow2013
Postsdbo
POMultiplying weight matrix of a trained neural network with a test vector
 

Note that there are some explanatory texts on larger screens.

plurals
  1. POMultiplying weight matrix of a trained neural network with a test vector
    primarykey
    data
    text
    <p>I trained the perceptron neural network and obtained the weight matrix using matlab.</p> <p>The dimension of the obtained weight matrix is &lt;50x1 double></p> <p>Now while giving the test input, I have a &lt;1x1 double> value, that need's to be tested.</p> <p>If I multiply the weight matrix with the value, I get &lt;50x1 double>. How can I set threshold for &lt;50x1 double> value.</p> <p>Is there any way to get around this problem ?</p> <p>This is the code</p> <pre><code>tic clc; clear all; close all; %function [ w1, bias ] = percep1( x ) zzz = xlsread('D:\matlab\NN_FILES\train_mean.xlsx') s = zzz; learning_rate = 0.1; % go with the loop mohan theta = 10000; w1=0; for j = 1:50 x=s(:,j);t=1; bias=0; stopp=1; count=0; while stopp yin = bias + (w1*x); % activation function if yin &gt; theta y = 1; elseif yin &lt; -theta y = -1; else y = 0; end if (t ~= y) % for i = 1 : 7 %if ( x(i) ~= 0 ) w1 = w1 + ( learning_rate * t * x); %end % end bias = bias + ( learning_rate * t); end count = count + 1; if t==y stopp = 0; count; end end w(j,:) = w1; b1(j) = bias; e1(j) = count; end new_weights_2 = w(50,:) yyy= xlsread('D:\matlab\NN_FILES\test_mean.xlsx'); st=yyy; theta2 = 1.0e+04 * 1.2 ; for j=1:20 x=st(:,j); yin=(new_weights_2(1))*(x) output(j) = yin; if yin &gt; theta2 y = 1; elseif yin &lt; -theta2 y = -1; else y = 0; end y1(j)=y; end toc </code></pre> <p>Now I have used only the first value of the weight matrix inorder to satisfy the multiplication rule. Is there any way to multiply the weight matrix with the test input ?</p>
    singulars
    1. This table or related slice is empty.
    1. This table or related slice is empty.
    1. PTQuestion
    1. USMrk
    1. USMrk
    plurals
    1. This table or related slice is empty.
    1. This table or related slice is empty.
    1. This table or related slice is empty.
    1. This table or related slice is empty.
    1. This table or related slice is empty.
    1. COCan you show exactly what you are doing? Not the whole code but the final step with multiplication including variable size and class.
      singulars
      1. POMultiplying weight matrix of a trained neural network with a test vector
      1. USyuk
    2. COYour perceptron seems to map 7 input to 50 output. So clearly you need a 7 input vector at input, and a weighting function to map the 50 element output for comparison with a threshold, indicating true/false value. Seems like you may not be getting all details of your algorithm right. http://en.wikipedia.org/wiki/Perceptron
      singulars
      1. POMultiplying weight matrix of a trained neural network with a test vector
      1. USArcturus
    3. CO@yuk I have updated the question with the full code. Could you please assist me.
      singulars
      1. POMultiplying weight matrix of a trained neural network with a test vector
      1. USMrk
 

Querying!

 
Guidance
A row detail

Detail views are divided into sections. All the information in the data section comes from columns in the selected row. The other sections display data from other, related rows.

Related data can be related in a to-one or a to-many fashion. Captions of data related in a to-many fashion link to a list view showing a filtered view of the table.

Try moving around until you find a non-empty to-many entry and click on the label to get to one. You can move back to the root by clicking on the database name in the header.

SQuiL has stopped working due to an internal error.

If you are curious you may find further information in the browser console, which is accessible through the devtools (F12).

Reload