You are on page 1of 2

1. What is principle component analysis (PCA)?

Explain the difference between


supervised and unsupervised machine learning?

2. How do you handle missing or corrupted data in a dataset? What is meant by


‘Training set’ and ‘Test Set’ in supervised leaning?

3. What is semi-supervised machine learning? What are the applications of supervised


machine learning in modern businesses?

4. How will you know which machine learning algorithm to choose for your
classification problem? What is kernel SVM and what is the purpose of using kernel
SVM for classification? How do you design an email spam filter?

5. What are the different algorithm techniques in machine learning? When does
regularization becomes necessary in machine learning? What is data augmentation?
Give some examples?

6. What is ensemble learning? Give an example.


7. You have built a random forest model with 10000 trees. You got delighted after
getting training error as 0.00. But the validation error is 34.23. What is going on?
Haven’t you trained your model perfectly? Justify it.
8. Explain the KNN algorithm.

9. What is clustering in machine learning? How to find optimal K in K-means


clustering?

10. What is epoch and batch size in the training of machine learning models? What is cost
function and how to optimize cost function?

11. What is the difference between the two types of Hierarchical Clustering?

12. Define clustering. What are the different types of clustering explain in detail?

13. What is bagging and boosting in Machine Learning? Explain with examples. What is
the difference between L1 and L2 regularization?

14. What are the conditions in which Gradient Descent is applied?


15. Explain DBSCAN algorithm. What is the advantage of DBSCAN over K-means
clustering?
16. Assume you want to cluster 7 observations into 3 clusters using the K-Means
clustering algorithm. After the first iteration, clusters C1, C2, C3 have following
observations:
C1: {(2,2), (4,4), (6,6)}
C2: {(0,4), (4,0)}
C3: {(5,5), (9,9)}
17. What will be the cluster centroids if you want to proceed with the second iteration?

18. What is a confusion matrix? How to calculate accuracy from the confusion matrix?

19. What are Type I and Type II Errors? Why dimensionality reduction is necessary?

20. What is What is AUC-ROC curve and what does it represent?

21. What do you understand by Precision and Recall? What is the F1 score and how
would you use it? What is the trade-off between bias and variance?
22. How would you handle an imbalanced dataset? How to evaluate the performance of a
classifier in an imbalanced dataset? How to measure the performance in a regression
model?
23. What is deep learning? Discuss its importance in modern technology?
24. What is the role of activation function in ANN? Explain giving examples.

25. Explain basic models of artificial neural network. What is single layer perceptron?

26. Explain the terms axon, cell body, synapse and dendrite in biological neuron?
Compare biological neuron with the ANN.

27. What does ANN mean? What are its characteristics? Distinguish between human
brain and ANN. Explain in brief application areas of ANN.

28. Compute the output of the following neural network model having (2, 2, 1) structure
with linear activation function in the input layer and sigmoidal in the output layer, if
the input vector is [1.2, 0.5], weight vectors are [0.04 0.05; 0.2 0.02] and [0.06 0.15]
respectively.

29. Discuss the following major components of a generalized ANN model: processing
units; states of activation; output signals of the units; patterns of connectivity; and
activation rule.

30. What is the difference between CNN & RNN. Explain its applications.

You might also like