Q6. XNOR MLP Doubt

#1

For this question let us take True = +1 and False = -1. Consider the Multilayer perceptron network shown in the figure with 2 inputs. X1 and x2 and 4 perceptrons in the hidden layer. The outputs of these 4 perceptrons are denoted by h1, h2,h3,h4. Each input is connected to all the 4 perceptrons with specific weights represented by red and blue edges in the figure below. The bias (w0) of each perceptron is -2. Each of these perceptrons is connected to an output perceptron by weights w1,w2,w3,w4. The output of the perceptron (y) is the output of the network. We have to find the weights w1,w2,w3,w4 such that this network represent the truth table of XNOR boolean function with 2 inputs. Imgur Under which of the following condition will the above network behave as XNOR boolean function?

Tell me how to approach this problem?

#2

hey @rishitagoel13 ,
For such questions you need to start by making the truth table. So here you can make a truth table for XNOR gate using x1 and x2 as input variables. Then compute the values of h1,h2,h3,h4 by multiplying by weights and adding the bias. After that you need to look up for what values of w1,w2,w3 and w4 will the output be the same as expected from a XNOR gate.

I hope this helps.

#3

I hope I’ve cleared your doubt. I ask you to please rate your experience here
Your feedback is very important. It helps us improve our platform and hence provide you
the learning experience you deserve.

On the off chance, you still have some questions or not find the answers satisfactory, you may reopen
the doubt.