UNIT 1

1) What is PEAS? Mention it for Part picking robot and Medical Diagnosis system.
2) State and explain the agent structure in detail.
3) Explain A* search Algorithm. Also explain conditions of optimality of A*
4) Explain Greedy Best First Search Strategy.
5) Define Al. State its applications.
6) Define heuristic function. Give an example heuristic function for solving an 8-puzzle
problem.
7) Write states, Initial States, Actions, Transition Model and Goal test to formulate 8
Queens problem.
8) Explain following task environments
i) Fully observable vs. partially observable
ii) Discrete Vs Continuous
iii) Known Vs Unknown
iv) Single Agent vs. Multiagent
v) Episodic vs. Sequential
vi) Deterministic vs. Stochastic
9) Explain Simple Reflex Agent
10) Explain Model Based Agent.
11) What is Al? Write about the History of Al
12) State different foundations that led to the growth of Al
13) Describe Utility based agent.
14) Describe Goal based agent.
15) Describe a Learning agent in detail.
16) Explain Depth First Search(DFS) strategy in detail.
17) Explain Breadth First Search (BFS) strategy along with its pseudocode.
18) Explain Uniform Cost Search with suitable examples
19) Write a short note on Depth Limited Search Strategy.
20) Write a short note on Iterative Deepening Depth First Search Strategy.
21) What is PEAS? Explain with two suitable examples
22) Write a short note on Bidirectional Search.
23) Explain Thinking rationally and Acting rationally approaches of AI.
24) Write a short note on Thinking Humanly and Acting Humanly approaches of Al.
25) Describe problem formulation of vacuum world problem.
26) Explain Artificial Intelligence with the Turing Test approach.
27) Explain Recursive Best-First search algorithm.
28) Define Al.Explain different components of Al.
29) What are various informed search techniques? Explain in detail
30) What are various uninformed search techniques? Explain in detail
31) Write states, Initial States, Actions, Transition Model and Goal test to formulate Toy
problem.
32) Give the difference between DFS and BFS.
33) What is an Agent? Describe structure of intelligent agents.
34) Give the difference between Unidirectional and Bidirectional search methods.

Unit No: 02
1) What do you mean by Regularization? How does it work?
2) Describe Reasoning in First Order Logic (FOL).
3) What is Knowledge Representation? What are different kinds of knowledge that need
to be represented?
4) Write a short note on the Al Knowledge cycle.
5) What is an Artificial Neural Network?
6) What are the similarities and differences between Reinforcement learning and
supervised learning?
7) Explain Single-layer feed forward neural networks.
8) Write a short note on Multilayer feed forward neural networks.
9) Explain the Restaurant wait problem with respect to decision trees representation.
10) Write a short note on Inductive Reasoning
11) Explain Modus Ponens with an example.
12) What are the main components of PDDL?
13) What is the role of planning in Artificial Intelligence?
14) Write a short note on Propositional Logic
15) What is Backpropagation Neural Network?
16) What is an artificial neuron? Explain its structures.
17) Write a short note on Support Vector Machines.
18) Write a note on the Nearest Neighbour model.
19) Write a note on overfitting in the decision tree.
20) Differentiate between Supervised & Unsupervised Learning.
21) Differentiate between Linear Regression & Logistic Regression.
22) What is propositional Logic in Al?
23) Explain following knowledge representation technique-
a) Logical Representation
b) Semantic Network Representation
c) Frame Representaion
d) Production Rule
24) Explain the concept of First Order Logic in Al.
25) Write note on-
a) Universal Quantifier
b) Existential Quantifier
26) Explain Entropy, Information Gain & Overfitting in Decision tree.
27) Discuss different forms of learning Models
28) Discuss different forms of Machine Learning learning
29) Write a note on K-Nearest Neighbours.
30) What are the logical connectives used in Propositional logic?
31) What are the types of Quantifiers used in First order Logic?
32) Write a note on Supervised Learning.
33) Write a short note on Deductive Reasoning.
34) How is reasoning done using Abductive Reasoning.
35) What is entropy? How do we calculate it?
36) Explain the concept of Fuzzy logic.
37) What are the various types of operations which can be performed on Fuzzy Sets?
38) Explain the architecture of the Fuzzy Logic System.
39) Explain any 5 membership functions of Fuzzy Logic Systems.
40) Explain Defuzzification process using any suitable method.
41) What are Parametric models? Give their advantages.
42) Explain the non-parametric models.
43) Explain the concept of Classification used in Machine learning.
44) What is Regression? What are its types?
45) Explain the following.
i) Simple Linear Regression
ii) Multiple Linear Regression
iii) Polynomial Regression
iv) Logistic Regression
46) What is Bias? What is Variance? What is Bias/Variance Tradeoff!
47) Explain the following-
a) Ridge Regression (L2 Norm)
b) Lasso Regression (LI Norm)
48) Describe the Ensemble learning.
49) What is Gradient Descent? How does it work?

Unit No: 03
1) Write a short note on statistical learning.
2) Explain Bayesian Learning with an example.
3) Write a short note on the Hidden Markov Model.
4) What is an EM algorithm? What are its steps?
5) Explain Maximum-likelihood parameter learning for Continuous models.
6) Write a short note on temporal difference learning
7) Explain applications of Reinforcement Learning.
8) Write a short note on Passive Reinforcement Learning.
9) Write a short note on statistical learning.
10) Explain Bayesian Learning with an example.
11) Write a note on Naive Bayes models.

12) Explain the concept of Reinforcement Learning.

13) What are hidden variables or Latent Variables? Explain with examples.
14) Describe adaptive Dynamic programming.
15) Explain Q- Learning in detail.
16) What are the metrics used to evaluate the strength of Association Rule Mining ?
17) Explain the concept of Unsupervised Learning.
18) Explain Q- Learning in detail.
19) What is Association rule mining?
20) Explain the following with respect to Association Rule Mining:
a) Support
b) Confidence
c) Lift