Scribd
Upload
3 views

Module-3-QB

The document is a question bank for a module on artificial intelligence, covering topics such as linear regression, decision trees, classification methods, and evaluation metrics. It includes questions on statistical concepts, model accuracy, and specific algorithms like naïve Bayesian classification and SVM. The questions are designed to assess understanding of machine learning techniques and their applications in data analysis and prediction.

Uploaded by

villanravi17
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
3 views

Module-3-QB

The document is a question bank for a module on artificial intelligence, covering topics such as linear regression, decision trees, classification methods, and evaluation metrics. It includes questions on statistical concepts, model accuracy, and specific algorithms like naïve Bayesian classification and SVM. The questions are designed to assess understanding of machine learning techniques and their applications in data analysis and prediction.

Uploaded by

villanravi17
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

ARTIFICIAL INTELLIGENCE QUESTION BANK

Module-3

1. If you are a data scien st asked to plan budget for adver sing for the adver sing example
used in the text, list out the ques ons that you will analyze the data for to plan the
adver sing budget for di erent media.

2. Explain simple linear regression. How are the co-e cients es mated?

3. Elaborate how closeness is measured using least squares criterion

4. Explain with suitable mathema cal expressions for Standard Error (SE), accuracy of
es ma ng the linear regression coe cients β0 , β1

5. Describe step by step, how you would establish that a predictor variable has a linear
rela onship with the output variable in linear regression model. [Table 3.1]

6. Explain using appropriate measures as to how you will assess the accuracy of a linear
regression model.

7. Explain mul ple linear regression model and the associated RSS metric for gauging the t.

8. Describe the null hypotheses to which the p-values given in Table 3.4 correspond. Explain
what conclusions you can draw based on these p-values. Your explana on should be
phrased in terms of sales, TV, radio, andnewspaper, rather than in terms of the coefficients
of the linear model. [Chapter-3 Ex-1]

9. Describe the general approach to classi ca on in machine learning.


10. Write the steps in decision tree construc on.
11. How are decision trees used for classi ca on? Explain with an example
12. Explain a. Gain Ra o
ti
ti
ti
ti
ti
ti
ti
ff
ti
ti
ffi
fi
fi
ti
ti
ti
ffi
ti
ti
ti
ti
fi
b. Gini Index

13. Explain common approaches of tree pruning


14. Why is tree pruning useful in decision tree induc on? What is a drawback of using a separate
set of tuples to evaluate pruning?
15. Why naïve Bayesian classi ca on called “naïve”? Brie y outline the major steps of naïve
Bayesian classi ca on algorithm
16. Explain the di erent metrics for Evalua ng Classi er performance.
17. Explain how well classi er can recognize tuples of di erent classes using confusion matrix
18. Explain the four addi onal aspects beyond accuracy-based measures that are used for
Comparing classi ers.
19. Explain a. Handout method and Random Subsampling
b. Cross valida on

20. Give sta s cal tests of signi cance for model selec on between any two classi ca on models
M1 and M2.
21. Compare classi ers based on cost-bene t and ROC curves
22. Construct a set of IF-THEN rules for the given decision tree [figure]

23. Compute the information gain and expected information of attribute age, needed to
classify a tuple in D using the following Table
ti
ti
ff
fi
fi
fi
ti
ti
ti
fi
fi
fi
ti
ti
fi
ti
fi
ti
ff
fl
fi
ti
1.

24. Discuss Bayesian Belief networks with an example.

25. Discuss SVM . How are they used in prediction.

You might also like