Artificial Intelligence Importants Questions

Artificial Intelligence Importants Questions For Exam Preparations

Unit 1: Introduction to Artificial Intelligence

1. Define Intelligence, Intelligent behavior, and Artificial Intelligence.
2. Explain AI based on thought process and behavior.
3. Differentiate between:
   • Hard (Strong) AI vs Soft (Weak) AI
4. Explain the foundations of AI.
5. Explain major applications of AI.
6. What is an Intelligent Agent? Explain its structure.
7. Explain properties of intelligent agents.
8. Explain PEAS description of agents with example.
9. Explain types of agents:
   • Simple Reflex
   • Model-based
   • Goal-based
   • Utility-based
   • Learning agent
10. Explain environment types (deterministic, stochastic, static, dynamic, observable, single/multi-agent).
11. What is the Turing Test? What characteristics should an agent have to pass it?

Very Important:Types of agents, PEAS, Strong vs Weak AI, Turing Test

Unit 2: Problem Solving Methods

1. Define a problem and explain state space representation.
2. Explain problem formulation and well-defined problems.
3. What is a Constraint Satisfaction Problem (CSP)?
4. Solve:
   • Cryptarithmetic problem (e.g. CROSS + ROADS = DANGER)
   • Water Jug Problem
   • N-Queens Problem
   • Graph Coloring Problem

5. Explain problem solving by searching.
6. Explain performance measurement of search strategies.
7. Explain General State Space Search.
8. Explain with example:
   • Breadth First Search (BFS)
   • Depth First Search (DFS)
   • Depth-Limited Search
   • Iterative Deepening DFS
   • Bidirectional Search
9. Solve N-Queens / Puzzle problem using uninformed search.

10. Explain Greedy Best-First Search.
11. Explain A* Algorithm with example.
12. Prove the optimality of A*.
13. Differentiate between informed and uninformed search.
14. Explain Hill Climbing and Simulated Annealing.

15. Explain Game Playing in AI.
16. Explain Minimax Algorithm with example.
17. Explain Alpha-Beta Pruning with cutoff example.
18. Explain Tic-Tac-Toe problem.
19. Explain Stochastic Games.

Very Important:A*, Minimax, Alpha-Beta pruning, CSP problems

Unit 3: Knowledge Representation and Reasoning

1. Define knowledge and explain its importance.
2. Explain issues in knowledge representation and solutions.
3. Explain knowledge representation systems and their properties.
4. Explain types of knowledge.
5. Explain role of knowledge in AI.

6. Explain Rule-based representation.
7. Explain Semantic Nets with example.
8. Explain Frames.
9. Explain Logic-based representation.

10. Explain syntax and semantics of propositional logic.
11. Explain CNF (Conjunctive Normal Form).
12. Explain Resolution algorithm with example.
13. Explain forward and backward chaining.
14. Explain limitations of propositional logic.

15. Explain First Order Predicate Logic (FOPL).
16. Explain syntax, semantics and quantifiers.
17. Explain Horn clauses.
18. Explain unification and lifting.
19. Convert FOPL to CNF with example.
20. Explain Resolution Refutation System (RRS).
21. Solve logic problems using resolution.

22. Explain uncertain knowledge.
23. Explain random variables, prior and posterior probability.
24. Explain Bayes Rule and its use.
25. Explain Bayesian Belief Network.
26. Explain reasoning in Bayesian networks.

Very Important:Resolution, CNF, FOPL, Bayesian Network

Unit 4: Learning

1. Explain machine learning concepts.
2. Explain rote learning.
3. Explain learning by analogy.
4. Differentiate between transformational and derivational analogy.
5. Explain inductive learning.
6. Explain explanation-based learning.
7. Differentiate between supervised and unsupervised learning.
8. Explain learning by evolution (Genetic Algorithm).

Very Important:Supervised vs Unsupervised, Learning by analogy

Unit 5: Neural Networks & NLP

1. Define Artificial Neural Network (ANN).
2. Explain mathematical model of neuron.
3. Explain types of neural networks:
   • Feed-forward
   • Feed-back
4. Explain activation function and its need.
5. Implement Perceptron algorithm for:
   • AND gate
   • OR gate
6. Explain Back Propagation Algorithm.
7. Explain Hopfield Network.
8. Explain Boltzmann Machines.

9. Define Natural Language Processing (NLP).
10. Explain steps in NLP.
11. Explain:
    • Syntax analysis
    • Semantic analysis
    • Pragmatic analysis
12. Why is pragmatic analysis important?

Very Important:Perceptron, Backpropagation, NLP stages

Unit 6: Expert System & Machine Vision

1. Define Expert System.
2. Explain architecture of an expert system.
3. Explain stages of expert system development.
4. Why is expert system important in AI?
5. Write applications of expert system.

6. Define Machine Vision.
7. Explain steps of machine vision.
8. Explain applications of machine vision.

Very Important: Expert system architecture & applications.

Note: This list is for reference purposes only, to help you prepare smartly and cover all the critical areas. Always review your class notes, teacher guidelines, and syllabus coverage.

Don’t use our content without permission. 📸⚠️

Thank you for sharing you everyone! If you’d like to share your notes, lab reports, solution, assignments, projects, or any other academic materials, feel free to contact us through social media (Uni Bytes), email us at unibytesofficials@gmail.com, or visit our website at www.unibytes.xyz.

We regularly provide updates on BCA news, results, exam routines, and other important information. Stay connected with Uni Bytes for all your academic needs

📢 Stay Connected with Us!

Follow us on social media for the latest updates, events, and more: