1. Consider the following training set of training samples (size =3): X₁ ( Length, m) X2( Weight, kg) 2 120 8 60 5 300 You'd like to use logistic regression (fw,b(x)

= o(WT.x+b)) to predict the type of animal from inputs X₁ and X2. a) Please use feature scaling (min-max normalization) to process the inputs X₁ and X2. Round the result to three decimal places. [4 marks] X₂ 0 1 0.5 12 Xnew = ŷ (Type of animal) O(Crocodile) 1(Snake) O(Crocodile) x-min(x) max(x)-min(x) 0.25 0 1 [1 mark] [3 marks,0.5 marks per number] b) Using the scaled inputs and the following loss function, please calculate the values of W₁, b₁ that you would expect to obtain upon running one iteration gradient descent with learning rate 0.1, initial parameters Wo= [1], bo = 0.5 (Round the result to four decimal places). L(f) = [-[y"Inf(x¹) + (1 − î”)ln (1 − ƒ (x²))] [16 marks]