26. Which of the following activation functions can avoid the vanishing gradient problem?
(A) ReLU
(B) tanh
(C) Sigmoid
(D) ELU
(E) None of the above

22. Consider the following C program code and statements (1)~(5). (1) node[1].num = 0 (2) node[1].num = 1 (3) node[2].ptr-＞num = 9 (4) node[9].ptr-＞ptr-＞num = 121 (5) node[9].ptr-＞num = 100 Which of the following statements is CORRECT? (A) (1)(3)(4)(5) (B) (1)(3) (C) (2)(3) (D) (2)(3)(4)(5) (E) (4)(5)

23. The following is a C program code: Which one of the following statements is CORRECT? (A) When a=8, b=5, c=6, then A is 81, B is 5. (B) When a=8, b=5, c=6, then A is 81, B is 6. (C) When a=8, b=5, c=6, then A is 17, B is 5. (D) When a=8, b=5, c=6, then A is 17, B is 6. (E) When a=8, b=5, c=6, then A is 16, B is 6.

24. Suppose there are 16 users in the system, and they use symmetric encryption to achieve confidential communication, how many keys need to be managed? (A) 125 (B) 256 (C) 120 (D) 128 (E) 160

25. Let a, b, c be three 8-bit operands to a carry-save adder and their values be a = 00010110, b = 01101101 and c = 01001110. What are carry outputs of this carry-save adder? (A) 01001110 (B) 00110101 (C) 01010110 (D) 00111010 (E) 01101101

27. What is the status of a process if the process stops because its time slot is over? (A) Waiting (B) Running (C) Ready (D) Sleeping (E) Terminated

28. In machine learning, a confusion matrix is a table that is often used to describe the performance of a classification model on a set of test data for which the true values are known. One can use the matrix to calculate the evaluation metrics, such as accuracy, precision, recall, and F1 score. Suppose a confusion matrix contains TP (true positive) = 900, FN (false negative) = 100, FP (false positive) = 50, and TN (true negative) = 950. What is the value of precision for the model? (A) 1850/2000 (B) 900/1000 (C) 900/2000 (D) 50/950 (E) 900/950

29. Suppose there is a two-input neuron with weights w1 = 3, w2 = 2, and bias b = 1.2. Let the activation function f be the ReLU (Rectified Linear Unit) function, defined as f(x) = max(0, x). Given the inputs p1 = -5 and p2 = 6. What is the output of this neuron? (A) 0 (B) 1.2 (C) 2.4 (D) -1.5 (E) -1.8

30. For a Generative Adversarial Network (GAN) that can produce images of cars, which of the following statements is TRUE? (1) The generator aims to learn the distribution of car images. (2) After training the GAN, the discriminator loss eventually reaches a constant value. (3) The generator can produce unseen images of cars. (4) The discriminator can be used to classify images as car vs. non-car. (A) (1) and (2) (B) (2) and (3) (C) (1), (2) and (3) (D) (2), (3) and (4) (E) (1), (2), (3) and (4)

1. If the ______ lasts any longer, the government will have to restrict the supply of water to homes and businesses. (A) drone (B) drought (C) dough (D) drain

2. The slow food movement aimed to promote and protect local and traditional foods at a time when industrial food production and globalization were on the ______. (A) toss (B) raise (C) soar (D) rise