Subject - Computer Science (DEEP LEARNING)

Please answer by 12:00pm IST Sunday (Jan 24) last date for assignment. Urgent Please.. I will 100% upvote

Following training set is given. Input x1 1 2 1 2 Input x2 1 1 2 2 Output y 0 1 1 1 Loss function is given by L = ; ; -f(x1;, x2;))2 + regularization where, n is the number of training data instances. Mapping function f(x1,x2)=w0+wlxl+w2x2. L2 regularization is used. [3+ 2+2=7 Marks] A. What will be the values of wo, wl and w2 that will minimize the loss function with 2=0? B. What will be the values of w0,wl and w2 that will minimize the loss function with 2= 0.25? C. If gradient descent is used for minimization, what will be the optimal value of learning rate that will lead to fastest convergence for a=0.25? Following training set is given. Input x1 1 2 1 2 Input x2 1 1 2 2 Output y 0 1 1 1 Loss function is given by L = ; ; -f(x1;, x2;))2 + regularization where, n is the number of training data instances. Mapping function f(x1,x2)=w0+wlxl+w2x2. L2 regularization is used. [3+ 2+2=7 Marks] A. What will be the values of wo, wl and w2 that will minimize the loss function with 2=0? B. What will be the values of w0,wl and w2 that will minimize the loss function with 2= 0.25? C. If gradient descent is used for minimization, what will be the optimal value of learning rate that will lead to fastest convergence for a=0.25