BCA Eight Semester Machine Learning Important Questions

BCA Eight Semester Machine Learning Important Questions for Exams Preparations

Unit 1: Introduction to Machine Learning

1. Explain the concepts of training, validation, and test data. Why is it important to separate a dataset into these three subsets? Differentiate between the three.
2. Discuss the bias-variance tradeoff. How does this concept relate to the performance of a machine learning model?
3. What is the difference between a generalization bound and a learning curve? How do they help in understanding the performance of a learning algorithm?
4. What is Machine Learning? Describe the types of learning with examples.
5. What is the need of Machine Learning? Explain with suitable applications.
6. What constitutes overfitting, and how can it be prevented? Give an example.
7. Discuss the feasibility of learning, error, and noise in ML systems.

Unit 2: Introduction to Supervised Learning

8. Define overfitting. How can you prevent it? Elaborate with a suitable example.
9. What is linear regression and how is it used to find the best fit line? Explain the gradient descent algorithm as a method for finding the best fit line.
10. Describe the Perceptron algorithm.
11. Explain the principles of a Support Vector Machine (SVM). How does it work to separate data with the maximum margin?
12. What is a decision tree? Explain entropy and information gain with ID3 algorithm. Construct a decision tree with a suitable dataset.
13. Compare decision trees and SVMs in terms of their strengths and weaknesses.

Unit 3: Bayesian and Instance-based Learning

14. Define Naïve Bayes algorithm. How does it work? Discuss its strengths and weaknesses compared to other classification algorithms like Support Vector Machines.
15. What is a Bayesian Belief Network?
16. Explain the K-nearest neighbor (K-NN) algorithm. Consider the following data points and a new data point Sija={Machine Learning = 60, GIS=80} and use the K-NN algorithm to evaluate Sija’s result.

17. Explain probability theory and Bayes’ rule with example.

Unit 4: Introduction to Unsupervised Learning and Dimensionality Reduction

18. Define K-means clustering and explain how the algorithm works. Consider the following data points:
    O1(1,1.5), O2(1,4.5), O3(2,1.5), O4(2,3.5), O5(3,2.5), O6(3,4). Use the K-means algorithm with k=2 to cluster these data points.
19. What is hierarchical clustering? Explain with an example.
20. Why is dimensionality reduction useful? Justify with applications.
21. Explain Principal Component Analysis (PCA).
22. Discuss different distance functions used in clustering.

Unit 5: Measures for Performance Evaluation of ML Algorithms

23. What is the confusion matrix and why is it needed for evaluating a machine learning model? Explain it with a suitable example.
24. Define sensitivity and specificity.
25. What do you mean by an ROC curve?
26. In a credit card fraud detection system, the algorithm flagged 50 transactions as fraudulent. Out of these flagged transactions, 45 were indeed fraudulent. Additionally, the algorithm didn’t flag 30 fraudulent transactions. Calculate the precision, recall, and F1-score for the fraud detection system.
27. What are misclassification costs? Why are they important in ML?
28. Explain the use of box plot and confidence interval in evaluating ML performance.

Note: This list is for reference purposes only to help you prepare smartly and cover all critical areas of Machine Learning. Always review your class notes, teacher guidelines, and syllabus coverage.

Don’t use our content without permission. 📸⚠️

Thank you for sharing you everyone! If you’d like to share your notes, lab reports, solution, assignments, projects, or any other academic materials, feel free to contact us through social media (Uni Bytes), email us at unibytesofficials@gmail.com.

We regularly provide updates on BCA news, results, exam routines, and other important information. Stay connected with Uni Bytes for all your academic needs

Don’t Forget to Follow Uni Bytes