Please show work

Selecting the best attribute at each node during decision tree learning is done by computing information gain of each attribute IG(A), and selecting the attribute with highest info. gain. Assume S is the complete sample at a certain node, Sv is the subsample having all examples with the same value for the attribute being evaluated, and H is the entropy function. Which of the following formulas correctly computes information gain? A. IG(A)= H(Sv)- (Sv/S)H(Sv) B. 16(A) H(S) - (Sv/S)H(Sv) C. IG(A) H(S) (S/Sv) H(Sv) D. IG(A)-H(Sv)-E(S/Sv) H(S) You are asked to design a two-input perceptron that implements the Boolean function XI OR X2 (not XI OR X2). Assume the independent weight is always +0.5 (assume WO +0.5). Which of the following values for W1 and W2 are valid (effectively implement the function)? B. WI=0.1, W2=-0.4 C. W-0.4, W2-0.4