Q4. Partial Derivative

#1

Let f(x) be the logistic function where f(x) = 1/(1+e^(-Wx-B)). The loss function L is taken as L = ((y-f(x))^2)/2. Here x, y are re constants and W, B are parameters that will be updated. In other words L is a function of W and B. Let the partial derivative of L with respect to W be ‘M’ and with respect to B be ‘N’. Calculate the value of ‘m’ and ‘n’.

N = (y-f(x))f(x)(1-f(x))x, M = (y-f(x))(1-f(x))x
N = (y-f(x))f(x)(1-f(x)), M = (y-f(x))f(x)(1-f(x))x
N = -(y-f(x))f(x)(1-f(x)), M = -(y-f(x))f(x)(1-f(x))x

Since while deriving, the negative sign gets cancelled. So option 2 is correct not 3.

#2

Q5. Boolean Perceptron 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? Increase the magnitude of the bias Decrease the value of weights Increase the value of weights Decrease the magnitude of the bias

#3

yes you are correct on this.

#4

check this out to better understand

#5

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.