We do perceptron$-$based error$-$driven machine learning in this question. The initial weight

vector is $W=[0,0]$ and the bias is $b=0.$ If the computed $Y$ value is zero $($i$.$e$.,$ neither

positive nor negative$),$ we still update W and b based on the sample's label. Now you are

given four samples that are processed in order.

Sample $1$: $x1=(-1,2),Y1=-1$;

Sample $2$: $x2=(-2,-2),Y2=+1$;

Sample $3$: $x3=(1,-1),Y3=-1$;

Sample $4$: $x4=(-3,1),Y4=-1.$

a$.$ What is the weight vector W and bias b after processing Sample $1?$

b$.$ What is the weight vector W and bias b after processing Sample $2?$

c$.$ What is the weight vector W and bias b after processing Sample $3?$

d$.$ What is the weight vector W and bias b after processing Sample $4?$

Please provide with the correct steps?