Scribd
Upload
6 views2 pages

Unit 1

The document is a question bank for a unit on Artificial Intelligence, covering various topics such as definitions, types of AI, learning systems, algorithms, and challenges in AI research. It includes questions on specific algorithms like Candidate Elimination and FIND-S, as well as concepts like inductive bias and concept learning. The questions are designed to assess understanding and application of AI principles and techniques.

Uploaded by

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

Unit 1

The document is a question bank for a unit on Artificial Intelligence, covering various topics such as definitions, types of AI, learning systems, algorithms, and challenges in AI research. It includes questions on specific algorithms like Candidate Elimination and FIND-S, as well as concepts like inductive bias and concept learning. The questions are designed to assess understanding and application of AI principles and techniques.

Uploaded by

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

Unit 1 Question Bank

1. Define Artificial Intelligence. How does AI differ from traditional computing


approaches?
2. List out the steps in designing a learning system with a suitable explanation.
3. What are the key components of an AI system? Explain with examples.
4. Describe the different types of AI, such as narrow AI, general AI, and superintelligent
AI. Provide real-world examples of each.
4. What is the "AI problem"? Explain the core challenges associated with it.
5. Why is it difficult to create AI systems that exhibit general intelligence?
6. Consider the Tic-Tac-Toe Game and Explore any two solutions to design the AI to play.
7. Discuss the primary objectives AI research aims to achieve.
8. What is the underlying assumption in AI? How does it guide the development of
intelligent systems?
9. Why is the underlying assumption important for creating intelligent behavior in
machines?
10. Consider the given below training example which finds malignant tumors from MRI
scans. Show the specific and general boundaries of the version space after applying
candidate elimination algorithm. (Note: Malignant is +ve, Benign is —ve). Describe
the same algorithm.
Example Shape size Color Surface Thickness Target
Concept
01 Circular Large Light Smooth Thick Malignant
02 Circular Large Light Irregular Thick Malignant
03 Oval Large Dark Smooth Thin Benign
04 Oval Large Light Irregular Thick Malignant
05 Circular Small Light Smooth Thick Benign

10. What are the limitations of this assumption in modern AI research?


11. What is an AI technique? How is it used in problem-solving?
12. Compare heuristic search techniques with machine learning techniques in AI.
13. Explain the difference between symbolic AI and connectionist AI techniques.
13. What is a well-posed learning problem in AI? What are its essential components?
14. Explain why defining a well-posed learning problem is important for machine learning.
15. Illustrate the process of creating a 3x3 magic square using the numbers 1 to 9. What
specific properties define it as a magic square, and what is the magic constant for this
square?
16. What role do hypotheses and data play in defining a well-posed learning problem?
16. Describe the steps involved in designing a learning system.
19. Apply the Candidate Elimination algorithm and determine the general hypothesis (G)
and specific hypothesis (S) for the given dataset.

17. Illustrate with an example the concept of Inductive bias.


18. What factors should be considered when choosing a learning algorithm for a system?
19. How does feedback from the environment influence the design of a learning system?
20. What is concept learning? How does it differ from other types of learning?
21. Illustrate the Find S algorithm in detail.
22. Explain the general-to-specific ordering in concept learning. Why is it useful?
23. Describe how the general-to-specific ordering can help in the search for the most
accurate hypothesis.
24. Imagine you are tasked with building a machine learning program to compete in a
checkers tournament. Apply the fundamental approaches to machine learning in the
design of a checkers-playing program and describe how it will help improve the
program's performance over time.
22. How can concept learning be viewed as a search problem?
23. What are the main challenges when treating concept learning as a search process?
24. Explain how hypothesis space and bias affect concept learning as a search task.
25. Define artificial intelligence and Explain tic tac toe algorithm using second approach
(POSSWIN).
25. What is the FIND-S algorithm, and how does it work?
26. Explain the limitations of the FIND-S algorithm in real-world applications.
27. How does the FIND-S algorithm handle noise in the data?
28. Apply the Candidate Elimination algorithm to the dataset and determine the general
hypothesis (G) and specific hypothesis (S) for John's enjoyment of sport.

28. What is a version space? How is it related to the concept of hypothesis elimination?
29. Describe the candidate elimination algorithm and how it works in concept learning.
30. What are the main advantages and disadvantages of using the candidate elimination
algorithm?
31. What is inductive bias in machine learning, and why is it important?
32. Give examples of different types of inductive bias used in learning algorithms.
33. How does inductive bias influence the performance and generalization of a machine
learning model?
34. Discuss the various stages involved in designing a learning system in brief
35. Analyze the given training example using candidate elimination algorithm and obtain
general and specific hypothesis:
Ex Eyes Nose Head color Hair Smile

1 Round Triangle Round Purple yes Yes

2 Square Square Square Green yes No

3 Square Triangle Round Yellow yes Yes

4 Round Triangle Round Green No No

5 Square Square Round Yellow Yes Yes

You might also like