Best 60+ Machine Learning MCQ With Revision Notes

Machine Learning MCQ: Machine learning is a branch of Artificial Intelligence which focuses on the development of algorithms and statistical models to enable computers to learn from data and improve their performance. The core concept behind machine learning is to allow computers to learn different patterns, make decisions based on the learning and make predictions.

Machine Learning MCQ With Revision Notes

The following steps are involved in the process of machine learning –

1. Data Collection : Data collection is important, first we have to collect data which will be used to train the machine learning model.
2. Data Preprocessing : Data should be clean and there should be no noise or inconsistencies otherwise it will hinder the learning process.
3. Model Selection : Select an appropriate machine learning algorithm based on the problem or the types of data available.
4. Model training : Use prepared data to train machine learning. During the training, the model learns from the input data only.
5. Model Evaluation : Use different testing methods to evaluate whether the machine has learned the right things and works well.
6. Model Deployment : Once the model is trained and evaluated, it can be deployed to make predictions and perform the intended task.

Types of Machine learning –

Broadly there are three different types of Machine learning.

1. Supervised Learning :
   a. Supervised Learning is the type of Machine Learning.
   b. Supervised Learning is based on labeled data to train algorithms.
   c. Supervised Learning algorithms can split the training dataset, validate the dataset and test the dataset.
   d. In supervised Learning based on the training dataset, the model can accurately predict the output.
   e. It solves a variety of real world problems like spam checking in an email, fraud detection, image recognition, speech recognition system etc.
   f. There are two types of Supervised Learning i) Regression ii) Classification
   • Regression – Regression algorithms are used when there is relation between input data and output data for example Weather forecasting and Market trends.
   • Classification – Classification algorithms are used when the data is based on Yes or No, True or False, Male or Female.
2. Unsupervised Learning :
   a. Unsupervised Learning is machine learning. In this technique the machines are not trained with training dataset.
   b. Unsupervised Learning learns from itself, this model can find the hidden patterns just like the human brain which can learn new things itself.
   c. Regression or classification is not applied directly to Unsupervised Learning.
   d. The main purpose of unsupervised learning is to group the data according to the similarities and base on the structure.
   e. Unsupervised Learning algorithms can identify the difference between can and dog.
   f. There are two types of Unsupervised Learning i) Clustering ii) Association
   • Clustering – It helps to group the objects into clusters and also helps to categorize them.
   • Association – It helps to find the relationships between the large data for example, If any person wants to buy a shirt but there is a chance to buy pant also.
3. Reinforcement Learning :
   a. Reinforcement Learning learns from the feedback based on Machine Learning.
   b. Reinforcement Learning learns automatically using feedback without any labeled data.
   c. The main goal of Reinforcement Learning is to improve the performance and collect maximum positive rewards.
   d. Reinforcement Learning solves specific types of problems like, Chess games, robotics etc.

Some of the important Algorithm used in Machine Learning

Linear Regression:
a. Linear Regression is most popular and easiest Machine Learning algorithms
b. Linear Regression uses statistical methods to make predictions like salary, age, price, sales etc.
c. Linear Regression helps to find how the dependent data is changing according to the value of independent data.

Decision Trees
a. Decision Tree is a Supervised Learning technique.
b. Decision Tree can be used in both classification and regression problems.
c. Decision Tree is a tree structure classifier which is connected with branches based on the decision rules where the leaf node represents the outcome.
d. It can find the solution based on graphical representation.

Support Vector Machines (SVM)
a. SVM is the most popular Supervised Learning algorithm.
b. SVM are used in Classification and Regression in both the areas.
c. SVM are used to find the best line or decision in the future.
d. The best decision boundary is known as hyperplane.

K-Nearest Neighbors (KNN)
a. Simplest Machine Learning algorithms based on Supervised Learning technique.
b. K-NN can classify similar data based on the available data.
c. K-NN can be used for both Regression and Classification.
d. K-NN can’t make any assumption on underlying data.
e. K-NN is also known as the lazy learner algorithm.

K-Means
a. K-Means based on Unsupervised Learning algorithm.
b. It can group the data in categories without any need of training data.
c. The algorithm takes an unlabeled dataset and splits the data into k-number of clusters and repeats the process until the algorithm does not find the best clusters.

Logistic Regression
a. Most popular Machine Learning algorithms.
b. Logistic Regression predicts the output based on dependent data.
c. The outcome of Logistic Regression is either Yes or No, 0 or 1, Ture or False.
d. Logistic Regression is similar to the Linear Regression.

Random Forest
a. Random Forest belongs to Supervised Learning.
b. It is used to solve complex problems and improve performance.
c. It contains a number of decision trees on various subsets.
d. Higher accuracy is based on a greater number of trees.

Machine Learning MCQ With MCQPrime

1. Which of the following machine learning algorithms is based on the concept of bagging?
   a. Decision Tree
   b. Support Vector Machines (SVM)
   c. Random Forest
   d. k-Nearest Neighbors (k-NN)

2. Identify the disadvantages of decision trees.
   a. Prone to overfitting
   b. Difficult to interpret
   c. Require large amounts of training data
   d. Slow to train

3. What is the term used to describe the process through which machine learning algorithms create models using sample data?
   a. Training
   b. Learning
   c. Modeling
   d. Prediction

4. Machine learning is a subset of _______________________.
   a. Artificial intelligence (AI)
   b. Data science
   c. Computer programming
   d. Robotics

5. __________ is a machine learning technique which helps to detect outliers in data?
   a. Classification
   b. Regression
   c. Clustering
   d. Anomaly detection

6. Identify the type of learning, which is used for labeled training data.
   a. Supervised learning
   b. Unsupervised learning
   c. Reinforcement learning
   d. Semi-supervised learning

7. In PCA (Principal Component Analysis), the number of input dimensions is equal to principal components.
   a. True
   b. False

8. Identify from the following in which dimensionality reduction reduces features are used.
   a. Feature extraction
   b. Feature selection
   c. Feature engineering
   d. Feature augmentation

9. ______________ is the father of machine learning programs.
   a. Alan Turing
   b. John McCarthy
   c. Geoffrey Hinton
   d. Andrew Ng

10. The most important phase in genetic algorithms is _____________.
    a. Selection
    b. Crossover
    c. Mutation
    d. Fitness evaluation

11. Which of the following issues in machine learning are frequently used?
    a. Classification
    b. Regression
    c. Clustering
    d. All of the above

12. Choose the false options regarding regression in AI.
    a. Regression is a type of supervised learning
    b. Regression predicts continuous values
    c. Regression can have multiple independent variables
    d. Regression cannot handle categorical data

13. Which of the following are successful applications of machine learning.
    a. Image recognition
    b. Natural language processing
    c. Fraud detection
    d. All of the above

14. Which of the following is not a type of learning _________.
    a. Supervised learning
    b. Unsupervised learning
    c. Reinforcement learning
    d. Creating common graph types

15. Which of the following learning algorithms is used to learn “facial identities for facial expressions”?
    a. Supervised learning
    b. Unsupervised learning
    c. Reinforcement learning
    d. Deep learning

16. Which of the model that was trained with only a single batch of data
    a. Batch learning model
    b. Online learning model
    c. Reinforcement learning model
    d. Single-batch learning model

17. Which of the correct applications is used in machine learning for a large database?
    a. Data mining
    b. Deep learning
    c. Big data analytics
    d. Pattern recognition

18. From the following which one of the numerical functions is incorrect for various function representations of machine learning.
    a. Linear regression
    b. Logistic regression
    c. Decision trees
    d. K-means clustering

19. The FIND-S algorithm ignores __________.
    a. Positive examples
    b. Negative examples
    c. Both positive and negative examples
    d. None of the above

20. Which one is the correct definition of neuro software:
    a. Software that simulates the behavior of a neuron
    b. Software used for neural network training
    c. Software for neurofeedback training
    d. None of the above

21. The generalized Delta rule is another name for the backpropagation law.
    a. True
    b. False

22. Choose whether the following statement is true or false: True error is defined over the entire instance space, and not just over training data.
    a. True
    b. False

23. CLT stands for _________________.
    a. Central Limit Theorem
    b. Confidence Level and Tolerance
    c. Continuous Learning Technique
    d. Cross-Language Transfer

24. Determine if the following statement is correct: The mechanism that enables a machine to learn and make judgments like humans is known as artificial intelligence.
    a. True
    b. False

25. Pick one of the following to represent the limitations of the backpropagation rule.
    a. Can get stuck in local minima
    b. Requires labeled training data
    c. Limited to feedforward neural networks
    d. All of the above

26. Which one of the following is an instance-based learner.
    a. Support Vector Machines (SVM)
    b. k-Nearest Neighbors (k-NN)
    c. Decision Tree
    d. Naive Bayes

27. Choose the correct advantages of CBR.
    a. It can handle complex and dynamic domains
    b. It can reuse past experiences
    c. It can provide explanations for its solutions
    d. All of the above

28. What are the difficulties of the k-nearest neighbor algorithm?
    a. Sensitive to the choice of k
    b. Computationally expensive for large datasets
    c. Requires feature scaling
    d. All of the above

29. How many types of layers in radial basis function.
    a. One
    b. Two
    c. Three
    d. It can vary

30. Which of the following is an application of CBR?
    a. Speech recognition
    b. Recommender systems
    c. Anomaly detection
    d. Text classification

31. Different search and optimization methods are used in machine learning. Choose one of the following that does not involve an evolutionary computation.
    a. Genetic algorithms
    b. Particle swarm optimization
    c. Simulated annealing
    d. K-nearest neighbors

32. Which of the following data are required for analyzing ML algorithms.
    a. Training the model
    b. Evaluating the model’s performance
    c. Interpreting the results
    d. All of the above

33. Select the metrics and tools that are most frequently used to evaluate classification models.
    a. Accuracy, precision, recall, F1 score, and confusion matrix
    b. Mean squared error, R-squared, and residual plots
    c. Silhouette coefficient, Rand index, and Davies-Bouldin index
    d. Area under the ROC curve, precision-recall curve, and lift curve

34. PAC stands for ____________.
    a. Probabilistic Approximation Condition
    b. Probably Approximately Correct
    c. Partially Accurate Classification
    d. Predefined Accuracy Criterion

35. Which of the following is not a part of machine learning?
    a. Supervised learning
    b. Reinforcement learning
    c. Unsupervised learning
    d. Deep learning

36. What does K stand for in the K-means algorithm?
    a. Kernels
    b. Key features
    c. Knowledge
    d. Number of clusters

37. Is it true or incorrect that “Decision tree cannot be used for clustering”?
    a. True
    b. False

38. In clustering method which takes care of variance in data.
    a. K-means clustering
    b. DBSCAN
    c. Agglomerative clustering
    d. Mean shift clustering

39. Which of the following terms is used in machine learning algorithms to build a model based sample data?
    a. Training set
    b. Validation set
    c. Testing set
    d. Hyperparameters

40. Which of the following does not belong to supervised learning?
    a. Linear regression
    b. Support vector machines
    c. K-nearest neighbors
    d. k-means clustering

41. What is unsupervised learning?
    a. Learning without a teacher or labels
    b. Learning with a teacher providing labels
    c. Learning with reinforcement signals
    d. Learning with both labeled and unlabeled data

42. Which of the following is not a machine learning algorithm?
    a. Random forest
    b. Logistic regression
    c. Decision tree
    d. Binary search

43. Which of the following is not belong to machine learning?
    a. Rule-based systems
    b. Expert systems
    c. Genetic algorithms
    d. Decision trees

44. Which of the methods is used for trainControl resampling.
    a. K-fold cross-validation
    b. Grid search
    c. Gradient descent
    d. Principal component analysis

45. Choose the one that produces the most popular graph kinds.
    a. Matplotlib
    b. Scikit-learn
    c. TensorFlow
    d. PyTorch

46. What is the name of the procedure, where a machine learning model’s parameters are changed to enhance its performance on a training dataset?
    a. Feature engineering
    b. Model evaluation
    c. Model training
    d. Model optimization

47. What is bagging in ensemble learning?
    a. Combining multiple models by averaging their predictions
    b. Training multiple models independently on different subsets of the training data
    c. Using a single model to make predictions
    d. None of the above

48. Which of the following is a disadvantage of decision trees?
    a. Prone to overfitting
    b. Difficulty in handling continuous data
    c. Lack of interpretability
    d. None of the above

49. Which statement is true for Machine Learning?
    a. It is a field of study within computer science
    b. It involves developing algorithms that can learn from and make predictions or decisions based on data
    c. It is used in various applications such as image recognition, natural language processing, and recommendation systems
    d. All of the above

50. Which of the following machine learning techniques helps to detect outliers in data?
    a. Principal Component Analysis (PCa.
    b. Support Vector Machines (SVM)
    c. k-Nearest Neighbors (k-NN)
    d. Linear Regression

51. __________ is ignored by the FIND-S algorithm.
    a. Noise in the data
    b. Attributes not present in the training data
    c. Incomplete training data
    d. All of the above

52. Select the correct definition of neuro software.
    a. Software used for simulating neural networks
    b. Software used for natural language processing
    c. Software used for data visualization
    d. Software used for speech recognition

53. What are the backpropagation rule’s restrictions from the following.
    a. It can get stuck in local optima
    b. It requires labeled training data
    c. It can be computationally expensive for large networks
    d. All of the above

55. The important stage of a genetic algorithm is ____________.
    a. Selection
    b. Crossover
    c. Mutation
    d. Fitness evaluation

56. Which of the following types of problems related to machine learning are frequently encountered?
    a. Classification
    b. Regression
    c. Clustering
    d. All of the above

57. What is regression ___________.
    a. Regression is a type of supervised learning.
    b. In regression, the target variable is discrete.
    c. Regression is used to predict continuous values.
    d. Linear regression is a popular regression algorithm.

58. Identify the successful applications of machine learning.
    a. Image recognition
    b. Natural language processing
    c. Fraud detection
    d. All of the above

59. Look for the numerical functions in the various machine learning functions that are erroneous.
    a. Activation functions
    b. Loss functions
    c. Cost functions
    d. Evaluation functions

Chapterwise MCQs on Artificial Intelligence

• Artificial Intelligence MCQ With Revision Notes
• Neural Network MCQ With Revision Notes
• Expert System MCQ With Revision Notes
• Deep Learning MCQ With Revision Notes
• Data Science MCQ With Revision Notes
• Computer Vision MCQ With Revision Notes
• Machine Learning MCQ With Revision Notes