1.
Consider the following Bayesian network, where F stands for Flu and C stands for Coughing. Find P(C).
Correct Answer
A. 0.35
Explanation
The correct answer is 0.35. This means that the probability of having a coughing symptom (C) is 0.35. This probability is determined by the Bayesian network, which takes into account the probability of having the flu (F) and the conditional probability of having a cough given the flu. The value of 0.35 indicates that there is a moderate likelihood of having a coughing symptom.
2.
Which of the following graphical models capture the Naive Bayes assumption, where c represents the class label and fi are the features.
Correct Answer
A. Option 1
Explanation
Option 1 captures the Naive Bayes assumption because it represents the class label (c) and the features (fi) as nodes in the graphical model. In a Naive Bayes model, it is assumed that the features are conditionally independent given the class label, and this assumption is reflected in the graphical model by the absence of edges connecting the feature nodes. Therefore, Option 1 is the correct choice for capturing the Naive Bayes assumption.
3.
Suppose you are given 7 Scatter plots 1-7 (left to right) and you want to compare Pearson correlation coefficients between variables of each scatterplot. Which of the following is in the right order?
1. 1<2<3<4
2. 1>2>3 > 4
3. 7<6<5<4
4. 7>6>5>4
Correct Answer
B. 2 and 3
Explanation
The correct answer is 2 and 3. In scatter plots, the Pearson correlation coefficient measures the strength and direction of the linear relationship between two variables. The order in which the scatter plots are presented indicates the order of their correlation coefficients. Answer 2 states that scatter plot 2 has a higher correlation coefficient than scatter plot 3, while answer 3 states that scatter plot 3 has a higher correlation coefficient than scatter plot 4. Therefore, the correct order is 2 and 3.
4.
Bayesian Network is a graphical model that efficiently encodes the joint probability distribution for a large set of variables .
Correct Answer
A. True
Explanation
A Bayesian Network is indeed a graphical model that is used to represent and efficiently encode the joint probability distribution for a large set of variables. It consists of nodes that represent variables and directed edges that represent probabilistic dependencies between the variables. This allows for efficient computation of conditional probabilities and inference in the network. Therefore, the statement is true.
5.
A fair coin is tossed three times and a T (for tails) or H (for heads) is recorded, giving us a list of length 3. Let X be the random variable which is zero if no T has another T adjacent to it, and is one othetwise. Let Y denote the random variable that counts the number of T's in the three tosses. Find P(X=1, Y=2).
Correct Answer
B. 2/8
Explanation
To find P(X=1, Y=2), we need to find the probability of having X=1 (at least one T has another T adjacent to it) and Y=2 (two T's in the three tosses).
Out of the 8 possible outcomes (2^3 = 8), there are two outcomes that satisfy both conditions: TTH and HTT. Therefore, the probability of having X=1 and Y=2 is 2/8, which simplifies to 1/4.
Hence, the correct answer is 2/8.
6.
To safeguard your house, you recently installed two different burglary alarm systems by two different reputable manufacturers that use completely different sensors for their alarm systems. Alarm1 means that the first alarm system rings, Alarm2 means that the second alarm system rings, and Burglary means that a burglary is in progress. Which one of the two Bayesian networks given below makes independence assumptions that are not true?
Correct Answer
B. 2
7.
Consider the following graphical model. Mark which of the following pair of random variables is independent giveh no evidence?
Correct Answer
A. A, b
Explanation
The pair of random variables a and b is independent given no evidence because they do not have any direct or indirect relationship. This means that the value of one variable does not affect the value of the other variable. Therefore, the occurrence or value of variable a does not provide any information about the occurrence or value of variable b, and vice versa.
8.
In the following Bayesian network A, B and C are Boolean random variables taking values in {True, False}. Which of the following statements is true?
Correct Answer
B. The value of C is given to be True. If the value of B changes from True to False the conditional probability of A, P(AIB) changes.
Explanation
If the value of C is given to be True, and the value of B changes from True to False, the conditional probability of A, P(A|B), changes.
9.
Which of the following necessitates feature reduction in machine learning?
Correct Answer
D. All of the above.
Explanation
In machine learning, feature reduction is necessary when there are irrelevant and redundant features, limited training data, or limited computational resources. Irrelevant and redundant features can negatively impact the accuracy and efficiency of the learning algorithm. Limited training data can lead to overfitting and unreliable predictions. Limited computational resources may require reducing the number of features to improve efficiency. Therefore, all of the mentioned factors necessitate feature reduction in machine learning.
10.
For which of the following cases Dimensional reduction may be used?
Correct Answer
D. Both A and B
Explanation
Dimensional reduction may be used for both data compression and data visualization. Data compression involves reducing the dimensionality of the data to reduce its size without losing too much information. Data visualization also benefits from dimensional reduction as it helps to visualize high-dimensional data in a lower-dimensional space, making it easier to interpret and understand. Therefore, both options A and B are valid cases where dimensional reduction may be used.