where f is the sigmoid function.predicted_prop(Obj,d,V) <- prop(Obj,a,I_1)& prop(Obj,b,I_2)& prop(Obj,c,I_3)& V is f(w_0 + w_1*I_1 + w_2*I_2 + w_3*I_3).
f(x)= 1/(1+e-x)(The only property of f you need for this exam is that f(x) > 0.5 if and only if x>0.)
Suppose that, after learning, the parameters had the following weights:
Suppose the neural network classifies as true any example where the predicted value for d is greater than 0.5
w0 -3 w1 2 w2 2 w3 4
prop(e_1,a,1). prop(e_1,b,1). prop(e_1,c,0).
if(b=1,if(a=1,true,false),if(c=1,false,true)).(which is equivalent to the example decision tree given in the previous problem).