Consider two perceptrons one denoting boolean AND and one denoting boolean OR. What are two ways to go from an AND perceptron to an OR perceptron?

#1

What do we mean by boolean AND perceptron ?
Does it mean -> that soma function of the neuron is multiplying the inputs.
z=w1x1wx2
and for Bolean OR
z=w1x1+w2*x2

Then how can we convert from one value of z to another ?

How to do the implementation of truth table in nural network?
#2

Hey @chiragwxN, for every perceptron network for boolean function we have
z = 1 if (w1x1 + w2x2 + b) >=0
z = 0 if (w1x1 + w2x2 +b) <0

Now for and perceptron,
x1 x2 z
0 0 0
0 1 0
1 0 0
1 1 1

Now we have already build this network,lets say weights w1 = 1 and w2 = 1 and b = -2 (other values also possible )

Now if we want to change it to or perceptron network than,
x1 x2 z
0 0 0
0 1 1
1 0 1
1 1 1

This can be done by first increasing the weights w1 = 2, w2 = 2, b = -2
or by decreasing the bias term w1 = 1, w2 = 1, b = -1.

Hope this resolved your doubt.
Plz mark the doubt as resolved in my doubts section. :blush:

1 Like
#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.

#4

The question asks for two ways to do this yet only option is correct.
It says that ‘increase the value of weights’ is incorrect and is showing ‘decrease the magnitude of the bias’ as correct. Why so?