MACHINE LEARNING LAB-VIVA QUESTIONS-–OSMANIA UNIVERSITY-CSE Department

 

MACHINE LEARNING LAB-VIVA QUESTIONS-–OSMANIA UNIVERSITY-CSE Department

 

UNIT-1

1.       Define Feature, Feature Vector and Feature space

2.       Define Machine Learning

3.       Distinguish Parametric and Nonparametric algorithms

4.       Define types of learning algorithm

5.       Define over fitting and under fitting

6.       Define Training data, Testing data and Validation set

7.       Explain bias variance tradeoff

8.       Define all the evaluation measures in machine learning (SSE, RMSE, CONFUSION MATRIX, PRECISION, and RECALL. FScore)

9.       What do you mean by unbalanced dataset

10.   Define Feature selection mechanism

 

UNIT-2

1.       Define Supervised Learning Algorithm

2.       Define classification, Give two difference between classification and Regression

3.       Differentiate between logistic regression and linear regression?

4.       State types of Logistic Regression?

5.       Define Linear Discriminant Analysis

6.       Define Naive Bayes algorithm and why we use Naive Bayes algorithm?

7.       What is meant by K Nearest Neighbor algorithm?

8.       What is Support Vector Machine? Explain Hyper planes and Support Vectors

9.       Explain Hard and soft margins with the help of sketch

10.   What are advantages and limitations of the Naive Bayes /Decision Tree/ K Nearest Neighbor/ Support Vector Machine

11.   Define cross validation and Holdout

 

 

UNIT-3

1.       Which is the best, Bagging or Boosting? Differences between Bagging and Boosting

2.       What is the difference between simple decision tree and random forest tree?

3.       Define Ensemble Learning

4.       Explain Linear SVM, non-linear SVM.

5.       How Naive Bayes Algorithms works?

6.       How does the Bayes algorithm differ from decision trees?

7.       What is the difference between simple decision tree and random forest tree?

8.       What is the difference between KNN and K means?

9.       Is K nearest neighbor supervised or unsupervised?

10.   What are advantages and limitations of KNN and K means?

11.   How to choose right value for K in KNN? How to choose the value of "K number of clusters" in K-means Clustering?

12.   Define Hierarchial Clustering and list types of Hierarchial Clustering

13.   Define Expectation Maximization Algorithm

14.   Define Fuzzy c-means algorithm

 

UNIT-4

1.       Define multilayer percerptron and the elements of multilayer percerptron

2.       What is Gradient Descent (GD) and its variants?

3.       Define Radial Basis Functions

4.       Define RNN. List the advantages and limitations of RNN

5.       What is deep learning? . Explain elements of Deep Learning?

6.       State difference between Machine Learning and Deep Learning.

7.       State different architectures of DL network

8.       What is activation Functions? Why activation functions are required?

9.       What is Loss/ Cost Function?

10.   What is Convolutional Neural Network (CNN)? Define the blocks of CNN

 

UNIT-5

1.       What is reinforcement learning? Explain with an example

2.       What is reinforcement learning? State one practical example.

3.       State key constituents of reinforcement learning. (Explain key terms in reinforcement learning.)

4.       How to represent the agent state?

5.       Explain Markov Decision Process

6.       What is 'Q' in Q-learning?

7.       Difference between Reinforcement Learning and Supervised Learning.

8.       Write the workflow of ML model:

9.       Explain optimizers. Why optimizers are required?

10.   Write the different stages of 1. Text Classification and Image Classification