Scribd
Upload
25 views2 pages

Ai & ML Question Bank For Cie-2

The document is a question bank for a course on Artificial Intelligence and Machine Learning, specifically covering Modules 3 and 4. It includes various questions related to machine learning concepts, workflows, applications, feature selection, model performance, and specific scenarios in healthcare and retail. The questions are designed to assess understanding at different Bloom's levels, ranging from definitions to detailed explanations and calculations.

Uploaded by

shivampoddar171
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
25 views2 pages

Ai & ML Question Bank For Cie-2

The document is a question bank for a course on Artificial Intelligence and Machine Learning, specifically covering Modules 3 and 4. It includes various questions related to machine learning concepts, workflows, applications, feature selection, model performance, and specific scenarios in healthcare and retail. The questions are designed to assess understanding at different Bloom's levels, ranging from definitions to detailed explanations and calculations.

Uploaded by

shivampoddar171
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 2

22CD52 ARTIFICIAL INTELLEGENCE AND MACHINE LEARNING

Question Bank
Modules- 3 & 4
Sl Question Mark Bloom’s
N s Level
O
1. Define machine learning and outline the key processes involved in a typical 6 L2
machine learning workflow.
2. Why is it essential to divide a dataset into training, validation, and test sets? 6 L4
Explain how this division impacts model performance and generalization.
3. Explain the role of cross-validation in preventing overfitting. Why is cross- 6 L4
validation particularly useful in smaller datasets?
4. Describe the machine learning lifecycle in detail, covering each stage from 10 L2
data collection to model deployment and monitoring.
5. List and explain the key applications of machine learning in various fields 10 L2
such as healthcare, finance, and e-commerce, with relevant examples.
6. What are feature sets in machine learning, and why are they critical to 10 L4
model performance? Illustrate with an example.
7. What is dimensionality reduction? State its significance considering some 6 L4
real time scenario.
8. Consider that you are working on a model to predict house prices, but the 10 L4
dataset contains hundreds of features. Describe how you would approach
feature selection and dimensionality reduction, and discuss why these steps
are crucial in this scenario.
9. A healthcare organization is developing a machine learning model to 10 L4
diagnose diabetes using patient data. They have a dataset with 50 features,
including age, gender, glucose levels, blood pressure, insulin, and skin
thickness.
Discuss which feature selection techniques would be appropriate for this
scenario. Explain how you would identify and retain the most relevant
features for diabetes diagnosis. Also identify the type of learning applied in
this case.
10. A dataset consists of 20 samples for a binary classification problem (Class A 10 L3
and Class B) with two features: Weather (Sunny, Rainy) and Temperature
(Hot, Cold). The dataset is as follows:
 Class A: Sunny-Hot (4 samples), Rainy-Cold (3 samples), Sunny-Cold
(3 samples)

 Class B: Sunny-Hot (2 samples), Rainy-Hot (4 samples), Rainy-Cold


(4 samples)
Calculate the entropy of the entire dataset. Then, calculate the information
gain for splitting on the "Weather" feature. Show all steps in your
calculations and explain how information gain would help in deciding the
root node of the decision tree.
11. A retail company wants to predict customer churn, identifying customers 6 L4
who are likely to stop using their service. They have a labeled dataset
containing historical data on customer interactions, including information
on service usage, customer support calls, payment history, and subscription
plans, along with a label indicating whether each customer eventually
churned.
How can supervised learning be applied to this problem? Which type of
Supervised Learning does it represent (Classification or regression). Justify
your answer.
12. A company wants to use machine learning to detect fraudulent transactions 6 L4
in real time. Explain the steps in the machine learning lifecycle that you
would follow, including the datasets and validation techniques required to
develop a robust fraud detection model.
13. List the types of networks involved in processing the data and explain each 6 L2
category in detail(ANN, CNN, RNN, Transformers).
14. Explain the steps involved in a Decision tree algorithm considering any 8 L3
sample dataset of choice. Also, list the hyperparameters of a decision tree
classifier.
15 What is overfitting and underfitting of the model and few measures taken 6 L2
to handle them.

You might also like