UNIT-I: Foundational Concepts in Artificial Intelligence
2-Mark Questions
● Define computational systems with examples.
● Differentiate between data and information.
● What is meant by rule-based knowledge representation?
● List two key applications of AI in daily life.
● Give two examples of AI jargon.
● State any two differences between intelligence and artificial intelligence.
● Describe the concept of problem formulation in AI.
● Name two domains where AI is important and briefly explain why.
● What is structural knowledge representation in AI?
● Mention one significant milestone in the history of AI.
● Define machine learning in simple terms.
● Differentiate between supervised and unsupervised learning.
● List and explain two limitations of AI.
● List two types of learning methods in AI.
● Give two real-world applications of computer vision.
3-Mark Questions
● Explain the importance of knowledge over information in AI with an example.
● Contrast rule-based and structural approaches to knowledge representation.
● Describe the historical development of AI from the 1950s to present.
● Illustrate how computational systems solve problems using AI methods.
● Discuss the relevance of AI in the healthcare sector.
● List and explain three common AI jargons used by practitioners.
● How does AI contribute to advancements in education?
● Discuss the differences in handling data and knowledge within AI systems.
● Explain the role of problem-solving in making AI systems intelligent.
● Briefly describe AI's impact on automation and robotics.
● Differentiate between supervised, unsupervised, and reinforcement learning with simple
examples.
● Discuss the role of machine vision in self-driving cars.
● Explain the contribution of Alan Turing to the field of AI.
5-Mark Questions
● "AI is transforming every industry." Justify this statement with suitable examples.
● Describe the role of problem formulation in building intelligent systems, providing
practical scenarios.
● Compare and contrast rule-based and structural approaches in knowledge representation
with diagrams.
● Discuss the evolution of AI and highlight critical breakthroughs over the years.
● Explain, with examples, the domains where AI applications are revolutionizing current
practices.
● Evaluate the importance of learning from data in modern AI methods.
● Discuss how AI mimics human intelligence, mentioning strengths and limitations.
● Analyze the significance of AI in solving real-world problems, giving recent case studies.
● Illustrate with examples the differences between information and knowledge.
● Explain various jargons in AI, and how understanding these helps AI applications
succeed.
● Evaluate the ethical challenges of AI adoption in society, citing at least two real-world
cases.
● Explain how AI contributes to sustainable development and smart cities.
UNIT-II: Data Exploration
2-Mark Questions
● Define quantitative and qualitative data with examples.
● List two characteristics of good data.
● What is a missing value in a dataset?
● Describe one method for handling missing values.
● State two data collection methods used in research.
● What do you mean by data visualization?
● Give examples of two types of data.
● Define data engineering.
● State any two drawbacks of poor data quality.
● Mention the difference between primary and secondary data.
● State two advantages of data preprocessing.
● Give two examples of data quality issues.
3-Mark Questions
● Explain the significance of data analysis in data exploration.
● How can data visualization assist in understanding complex datasets?
● Describe three different types of data collection methods.
● Discuss how missing values impact data analysis.
● Identify and explain three key data characteristics to consider before data analysis.
● How does data engineering contribute to the field of AI?
● Compare structured and unstructured data with examples.
● What are the steps involved in a typical data exploration process?
● Describe how to handle outlier values in data.
● Explain the difference between exploratory and confirmatory data analysis.
● Explain the importance of data preprocessing before applying machine learning
algorithms.
5-Mark Questions
● "Effective data visualization is vital for insightful data analysis." Discuss with examples
and tools.
● Propose a strategy for collecting, cleaning, and visualizing a new market research dataset.
● Explain with examples how missing values can be handled through imputation and
deletion.
● Compare and contrast at least three data collection methods for their application in AI
projects.
● Discuss data characteristics and their role in determining analysis techniques.
● Analyze the importance of data engineering in preparing data for artificial intelligence.
● With examples, explain how data analysis informs decision-making in business.
● Illustrate the process of data exploration using a case study or workflow diagram.
● Discuss challenges faced when working with real-world data and methods to overcome
them.
● How does domain knowledge assist in data analysis and exploration tasks?
Python Questions:
1. Write a Python program to print the first 10 natural numbers using a loop.
2. Take a number as input and check whether it is even or odd.
3. Write a program to find the largest of three numbers entered by the user.
4. Write code to calculate the factorial of a given number using a for loop.
5. Write a Python program to reverse a given string without using slicing.
6. Write a program to generate the multiplication table of a given number.
7. Given a list [1, 2, 3, 4, 5], write code to calculate the sum of its elements without using
sum().
8. Write a program to check if a string is a palindrome.
9. Write Python code to count how many vowels are in the string "programming".
10.Write a program to find the Fibonacci sequence up to n terms.
11.Write a program that takes a sentence as input and counts the number of words in it.
12.Write Python code to swap two numbers without using a third variable.
13.Write a program that prints all numbers between 1 and 50 divisible by 7.
14.Given a list [10, 25, 30, 45, 50], write code to print only the numbers greater than 30.
15.Write a Python program to convert Celsius temperature to Fahrenheit.
NumPy Practice Questions:
1. Create a NumPy array of numbers from 1 to 10 and print it.
2. Write a program to create a NumPy array of zeros with shape (3, 4).
3. Create a NumPy array of even numbers between 2 and 20.
4. Given arr = [Link]([5, 10, 15, 20]), find the sum of all elements.
5. Write a program to generate a 1D NumPy array of 10 random integers between 1 and 50.
6. Create a 3×3 identity matrix using NumPy.
7. Given an array [3, 6, 9, 12, 15], print only elements greater than 10.
8. Create a NumPy array of shape (2, 3) and reshape it into (3, 2).
9. Given arr = [Link]([2, 4, 6, 8]), multiply each element by 5 using
vectorized operations.
10.Write a NumPy program to find the maximum and minimum element of an array.
Pandas Practice Questions:
1. Read a CSV file named "[Link]" into a Pandas DataFrame and display the first 5
rows.
2. From a DataFrame containing ['Name', 'Age', 'Marks'], select only the "Marks" column.
3. Write a Pandas program to display the shape (rows and columns) of a DataFrame.
4. Given a CSV file "[Link]" with columns ['Product', 'Price', 'Quantity'], calculate the
total sales (Price × Quantity).
5. From a DataFrame, select rows where "Age" is greater than 25.
6. Write code to find the average marks of students from "[Link]".
7. Given a CSV file "[Link]" with columns ['Department', 'Salary'], find the
maximum salary in each department.
8. Write a Pandas program to drop rows with missing values from a DataFrame.
9. Fill missing values in the "Age" column of a DataFrame with the column’s mean.
10.From "[Link]", group data by "Product" and calculate the sum of "Quantity".
11.Write code to rename the column "Marks" to "Score" in a DataFrame.
12.Sort a DataFrame based on the "Salary" column in descending order.
13.From a CSV "[Link]", filter rows where "Marks" are between 50 and 80.
14.Write a Pandas program to save a modified DataFrame into a new CSV file called
"students_cleaned.csv".
15.Given a DataFrame with dates as a column, convert that column to Pandas datetime
format.