Check Your Knowledge Of AI/ML Fundamentals! #29
Hello Everyone,
Welcome to the 29th edition of my newsletter ML & AI Cupcakes!
The agenda of today’s newsletter is to have a quick knowledge check of AI/ML fundamentals.
For this, I have complied a practice set of MCQs from different topics.
The answers are provided at the end. But, please make sure you check them only once you have completed your test…:)
Good Luck!
Practice MCQs
1. Logistic regression assumes a linear relationship between the independent variables and log odds of the outcome variable.
a. True
b. False
2. What type of outputs are generated by a linear regression model?
a. Continuous Values
b. Categorical values
c. Both
d. None of the above
3. Huber Loss is a combination of _________.
a. MSE and MAE
b. MSE and RMSE
c. RMSE and MAE
d. None of the above
4. Type I error (False Positive) in a confusion matrix is more critical than Type II error (False Negative)?
a. True
b. False
c. It depends on the problem
5. Which Gradient Descent form uses the entire training dataset to compute gradient of loss function w.r.t. model parameters in each iteration?
a. Batch Gradient Descent
b. Mini-Batch Gradient Descent
c. Stochastic Gradient Descent
d. None of the above
6. Which of the following is used to handle missing values in ML?
a. Imputation
b. Cross-validation
c. Backpropagation
d. None of the above
7. Tree based algorithms (Decision Tree, Random Forest and GBM) require a linear relationship between the features and the target variable.
a. True
b. False
8. Which of the following is a type of missing values in ML?
a. Missing Completely at Random (MCAR)
b. Missing at Random (MAR)
c. Missing not at Random (MNAR)
d. All of the above
9. Which of the following is not a feature selection method in ML?
a. Filter methods
b. Wrapper methods
c. Normalization
d. Embedded methods
10. What is the possible range of values for Pearson’s correlation coefficient?
a. -1 to 1
b. 0 to 1
c. -0.5 to 0.5
d. 0 to 0.5
11. Pearson’s correlation coefficient measures the strength and direction of a linear relationship between two non-numerical variables.
a. True
b. False
12. K-fold cross-validation and Stratified K-fold cross-validation are same.
a. True
b. False
13. The size of test set in K-fold cross-validation and Stratified K-fold cross-validation are same.
a. True
b. False
14. Which technique ensures that each fold maintains a similar proportion of categories in the target variable as that of the entire dataset?
a. K-fold cross-validation
b. Stratified K-fold cross-validation
c. Both
d. None of the above
15. Which of the following techniques ensures that the chronological order of the data is maintained during the splitting process?
a. K-fold cross-validation
b. Stratified K-fold cross-validation
c. Leave-one-out cross-validation
d. Time Series cross-validation
16. The average of squared difference between predicted and actual values is known as ___.
a. Mean Squared Error (MSE)
b. Mean Absolute Error (MAE)
c. Huber Loss
d. None of the above
17. Which of the following Python library is used to train neural networks?
a. Scikit-learn
b. Keras
c. Numpy
d. Matplotlib
18. SMOTE is an ____________ technique.
a. Undersampling
b. Oversampling
19. Which of these algorithms most commonly face the vanishing gradient problem?
a. Random Forest
b. Decision Tree
c. Neural Networks
d. Logistic Regression
20. Which of the following metrics can't be calculated from a confusion matrix?
a. Accuracy
b. RMSE
c. Precision
d. Recall
21. Which metric is calculated by combining precision and recall into a single value, emphasizing the balance between the two?
a. Accuracy
b. Sensitivity
c. Specificity
d. F1-Score
22. Logistic Regression assumes that there is a linear relationship between independent variables and dependent variable.
a. True
b. False
23. What is the typical effect of increasing model complexity on bias?
a. Increases Bias
b. Decreases Bias
c. No effect on bias
d. None of the above
24. Parameters and Hyperparameters are same in Machine Learning.
a. True
b. False
25. Which of the following is not a technique to deal with imbalanced datasets in machine learning?
a. SMOTE
b. Tomek Links
c. ADASYN
d. Backpropagation
26. Which of the following steps comes after forward propagation in neural networks?
a. Weight Initialization
b. Backpropagation
27. Which of the following involves bagging?
a. Linear Regression
b. Logistic Regression
c. Random Forest
d. None of the above
28. The cost function for Linear Regression and Logistic Regression is same.
a. True
b. False
29. Which of the following is an Unsupervised Machine Learning algorithm?
a. Linear Regression
b. Decision Tree
c. Random Forest
d. K-Means Clustering
30. Which of the following is not a type of node in Decision Trees?
a. Root Node
b. Leaf Node
c. Decision Node
d. Floating Node
31. In Linear Regression, we try to _________ the sum of squared errors of the model to identify the line of best fit.
a. Minimize
b. Maximize
32. Normalization and Standardization are same in Machine Learning.
a. True
b. False
33. Which of the following replicates existing samples from the minority class in an imbalanced classification problem?
a. Random Oversampling
b. SMOTE
c. ADASYN
d. None of the above
34. SMOTE only duplicates existing samples from the minority class.
a. True
b. False
35. Standardization is also known as Z-score Normalization.
a. True
b. False
36. Which of the following is not a parameter in Neural Networks?
a. Weights
b. Biases
c. Min Samples Split
37. Which of the following is true in neural networks?
a. Iterations = total samples/batch size
b. Iterations = total samples*batch size
c. Iterations = epochs*batch size
d. Iterations = epochs/batch size
38. In neural networks, number of epochs is a ____________.
a. Parameter
b. Hyperparameter
39. Which of the following is a parameter in neural networks?
a. Learning Rate
b. Number of epochs
c. Weights
d. None of the above
40. Which of the following steps use chain rule to compute gradients in Neural Networks?
a. Forward Pass
b. Backward Pass
c. Initialization of weights
d. None of the above
41. What is the formula of calculating Recall using a confusion matrix?
a. TP/(TP+FP)
b. TP/(TP+FN)
c. TN/(TN+FP)
d. None of the above
42. Which of the following describes the rate at which weights are updated during backpropagation?
a. Learning Rate
b. Activation Function
c. Number of epochs
d. Loss Function
43. In terms of confusion matrix, recall and sensitivity are same.
a. True
b. False
44. Which of the following doesn't belong to basic neural networks?
a. Hidden Layer
b. Activation Function
c. Leaf Node
d. Neurons
45. Which of the following is not a node-splitting criteria in Decision Trees?
a. Gini Impurity
b. Entropy
c. Information Gain
d. Backpropagation
46. Which of the following is not an activation function in Neural Networks?
a. Backpropagation
b. Sigmoid
c. ReLU
d. Softmax
47. Decision Trees can be used for both regression and classification problems?
a. True
b. False
48. Which of the following is not a type of missing values in ML?
a. Missing Completely at Random (MCAR)
b. Missing Sometimes at Random (MSAR)
c. Missing at Random (MAR)
d. Missing Not at Random (MNAR)
49. Which term is added as penalty to the cost function in ridge regression?
a. Sum of squared coefficients
b. Sum of absolute coefficients
c. Sum of squared residuals
d. Sum of absolute residuals
50. Grid search is used for__________.
a. Hyperparameter Tuning
b. Remove Duplicate Observations
c. Outlier Removal
d. Missing Value Treatment
Answers
1. a 2. a 3. a 4. c 5. a 6. a 7. b 8. d 9. c 10. a
11. b 12. b 13. a 14. b 15. d 16. a 17. b 18. b 19. c 20. b
21. d 22. b 23. b 24. b 25. d 26. b 27. c 28. b 29. d 30. d
31. a 32. b 33. a 34. b 35. a 36. c 37. a 38. b 39. c 40. b
41. b 42. a 43. a 44. c 45. d 46. a 47. a 48. b 49. a 50. a
Writing each newsletter takes a lot of research, time and effort. Just want to make sure it reaches maximum people to help them grow in their AI/ML journey.
It would be great if you could share this newsletter with your network.
Also, please let me know your feedbacks and suggestions in the comments section. That will help me keep going. Even a “like” on my posts will tell me that my posts are helpful to you.
See you soon!
-Kavita