(2,"0_) =(3,-0.2, -1), Prob. 1. Consider a single neuron with input (21, 12, 13), weight factor given by (wo, w1, W2, W3), and the activation function is the logistic function. (a) If the input to the neuron is (21, 22, 23) = (0.3,5,-2), and the weight vector for the neuron is (wo, W1, W2, W3) = (0.5, 2, -0.2, 1.5). Compute the output value y, and give the corresponding classification result. (b) Assume the logistic loss function given on page 8 of Chapter 39. If the data set and the labels are given as follows, compute the cost function (logistic function) value if the weight vector is (wo, w1, W2, W3) = (0.5, 2, -0.2, 1.5). 9,22), 13)) = (0.3, 5, -2), 9,22,252)) = (-1,0.5, 0.7), 9,22,2,3)) = (6,-3, 4), (3) (1) = 1; (2) = 0; (3) = 1; (4) = 1; (5) = 0. (264), 2)) = (0.8, -0.1, 2), (c) We need to train the neuron. After a few steps of training using batch training, the weight vector is (wo, w1, W2, W3) = (0.5, 2,-0.2, 1.5). Suppose the data and labels are given as above, compute the update to the weight vector when the learning rate n = 0.01 in the next step training. (d) After a few steps of training using on-line learning, the weight vector is (wo, W1, W2, W3) (0.5, 2, -0.2, 1.5). Suppose the data and labels are given as above, compute the update to the weight vector when the learning rate n = 0.01 with the first data point in the next step training. (2,"0_) =(3,-0.2, -1), Prob. 1. Consider a single neuron with input (21, 12, 13), weight factor given by (wo, w1, W2, W3), and the activation function is the logistic function. (a) If the input to the neuron is (21, 22, 23) = (0.3,5,-2), and the weight vector for the neuron is (wo, W1, W2, W3) = (0.5, 2, -0.2, 1.5). Compute the output value y, and give the corresponding classification result. (b) Assume the logistic loss function given on page 8 of Chapter 39. If the data set and the labels are given as follows, compute the cost function (logistic function) value if the weight vector is (wo, w1, W2, W3) = (0.5, 2, -0.2, 1.5). 9,22), 13)) = (0.3, 5, -2), 9,22,252)) = (-1,0.5, 0.7), 9,22,2,3)) = (6,-3, 4), (3) (1) = 1; (2) = 0; (3) = 1; (4) = 1; (5) = 0. (264), 2)) = (0.8, -0.1, 2), (c) We need to train the neuron. After a few steps of training using batch training, the weight vector is (wo, w1, W2, W3) = (0.5, 2,-0.2, 1.5). Suppose the data and labels are given as above, compute the update to the weight vector when the learning rate n = 0.01 in the next step training. (d) After a few steps of training using on-line learning, the weight vector is (wo, W1, W2, W3) (0.5, 2, -0.2, 1.5). Suppose the data and labels are given as above, compute the update to the weight vector when the learning rate n = 0.01 with the first data point in the next step training