Qp. Qp.

CO
Part-A (10 x 2 = 20 Marks)
No. U
NT

1. 1 Define Artificial Intelligence.

1. 2 Differentiate Natural Intelligence from Artificial Intelligence

1. 3 What are the different types of problem?

1. 4 What are software agents?

1. 5 Define Agent Function.

1. 6 Why we need Artificial Intelligence.

1. 7 Why are condition-action rules important in the design of an agent?

1. 8 Give the structure of an agent in an environment

1. 9 What is important for task environment?

1. 10 Give Structure of Simple Reflex Agent

2. 1 Define Breadth first search.

2. 2 Define Depth first search.

2. 3 Define iterative deepening depth-first search.

2. 4 Will Breadth First Search always find the minimal solution if more
than one solution exist? Why?

2. 5 Define depth limited search.

2. 6 Explain Uniform cost Search.

2. 7 Differentiate informed and uninformed search strategies.

2. 8 Define Informed search algorithm.

2. 9 Define Heuristic search.

2. 10 What are the advantages of Depth-First Search algorithm?

3. 1 Represent the following sentence in predicate form “All the children

likes sweets”.

3. 2 What are the elements and symbols of First order logic.

3. 3 What are the three families of First-order inference algorithms?

3. 4 What are the four parts of knowledge in first-order logic

3. 5 Define the first order definite clause.

3. 6 Define terms.

3. 7 Explain the significance of atomic sentences in predicate logic and give

a brief example.

3. 8 Define an atomic sentence and provide an example.

3. 9 Differentiate between a simple and a complex sentence, providing an

example of each.

3. 10 Explain how conjunction and disjunction operators are used to form

complex sentences in logic, and provide a simple example of each.

4. 1 Define planning in the context of artificial intelligence

4. 2 What is the primary goal of planning in AI systems?

4. 3 Explain the role of search algorithms in planning.

4. 4 Discuss the importance of domain modelling in planning.

4. 5 How do planners handle uncertainty and incomplete information in

real-world scenarios?

4. 6 Describe the difference between classical planning and heuristic

planning.

4. 7 Define mental events

4. 8 Explain the difference between mental events and mental objects.

4. 9 Define mental objects.

4. 10 Define Resolution

5. 1 What Is Learning?

5. 2 What is Supervised Learning?

5. 3 Why we need learning in AI.

5. 4 List out the purpose of Learning.

5. 5 Explain different Forms of Learning.

5. 6 Give two examples of learning.

5. 7 Describe the concept of labeled data in supervised learning and its

significance.

5. 8 Explain the role of training data and test data in supervised learning,
 emphasizing their importance for model evaluation.

5. 9 Define supervised learning and provide an example.

5. 10 What are the two main types of supervised learning tasks?

6. 1 What is un-supervised learning?

6. 2 What is reinforcement Learning?

6. 3 What is Bayesian Network?

6. 4 Illustrate CART?

6. 5 How CRM works in Al?

6. 6 List out some of the use of unsupervised learning.

6. 7 Define classification.

6. 8 Define Regression.

6. 9 Why we need classification. Give one example.

6. 10 Mention the types of regression models

7. 1 What are some common motivations for utilizing machine learning in

various fields?

7. 2 Can you provide examples of applications where machine learning is

commonly used?

7. 3 Explain the concept of ensemble learning in machine learning.

7. 4 Can you describe the process of reinforcement learning?

7. 5 What distinguishes unsupervised learning from supervised learning?

7. 6 Define machine learning

7. 7 What is the origin of machine learning, and how has it evolved over
time?

7. 8 Discuss some common uses and potential abuses of machine learning

technology.

7. 9 Can you provide examples of successful cases where machine learning

has made a significant impact?

7. 10 How do machines learn, and what are the fundamental principles

behind machine learning?

8. 1 What is generalization in the context of machine learning, and why is it

 important?

8. 2 What factors should be considered when applying machine learning to

a problem?

8. 3 How can the success of a machine learning model be assessed?

8. 4 What are some commonly used metrics for evaluating classification

methods?

8. 5 List out some of the metrics for evaluating classification methods.

8. 6 Describe the general machine learning process.

8. 7 How does the choice of input data impact the selection of a machine
learning algorithm?

8. 8 Draw General ML architecture

8. 9 Illustrate linear Regression

8. 10 List any 3 machine learning classification algorithms.

9. 1 Describe K-means Clustering.

9. 2 Define Sensitivity Analysis.

9. 3 Explain Casual Learning.

9. 4 Describe Decision Trees for Credit Card Promotion.

9. 5 Explain the Ideal Procedure for Cross Validation

9. 6 What is Information Gain in Decision Trees?

9. 7 Define Attribute Selection Measure: Entropy.

9. 8 Define Multi-Armed Bandit Algorithms.

9. 9 Describe Decision Tree: Weekend Example.

9. 10 Define Clustering in unsupervised learning.

10. 1 Explain the Concept of Automated Discovery.

10. 2 What are Influence Diagrams Used For?

10. 3 Explain Parameter Estimation.

10. 4 How is Overfitting Detected?

10. 5 What is Overfitting in Machine Learning?

10. 6 Explain Occam's Razor in the Context of Decision Trees.

10. 7 Describe an Algorithm for Building Decision Trees

10. 8 Explain Converting a Tree to Rules

10. 9 What is Risk Modeling?

10. 10 What is Risk Modeling in Decision Making?

Part – B ( 5 x 13 = 65 Marks)

11.a. 1 Define an agent in the context of artificial intelligence. Explain the key
components of an agent and how they interact to achieve intelligent
behavior. Provide examples to illustrate your explanation.

11.a. 2 Explain in detail about Agents and Environment.

11.a. 3 Illustrate structure of the agent with neat diagram.

11.a. 4 Explain in detail about simple reflex and Model based reflex agent.

11.a. 5 Illustrate Goal based and utility based reflex agent.

11.a. 6 Explain Learning agent and Model based reflex agent with neat
diagram.

11.a. 7 Elaborate on the relationship between Agents and Environments in AI.

Explain how Agents interact with their environments to accomplish
tasks, considering the key elements involved

11.a. 8 Provide an in-depth explanation of Simple Reflex and Model-based

Reflex agents. Discuss their characteristics, mechanisms, and
applications within the context of artificial intelligence.

11.a. 9 Define an agent within the realm of artificial intelligence. Describe the
essential components of an agent and how they collaborate to
demonstrate intelligent behavior. Use examples to support your
explanation.

11.a. 10 Illustrate Goal-based and Utility-based Reflex agents. Explain the

differences between them and how each type operates to achieve its
objectives. Use examples to clarify your points.

11.b. 1 Define informed search algorithms in the context of artificial

intelligence.

11.b. 2 Compare and contrast informed search algorithms with uninformed

search algorithms, highlighting their differences in terms of search
strategies and problem-solving efficiency.

11.b. 3 Explain the concept of heuristic functions in informed search

algorithms. Discuss how heuristic functions are used to guide the
search process towards the goal state.
11.b. 4 Describe the A* search algorithm in detail. Discuss how A* combines
information from both the cost to reach a node (g-value) and the
estimated cost to reach the goal from that node (h-value) to make
informed decisions during the search process.

11.b. 5 Describe in detail about Breadth first search and Iterative deepening
depth-first Search algorithm in detail.

11.b. 6 What are the five Uninformed search strategies? Explain any two in
detail with example

11.b. 7 Explain the working principle of BFS and DFS with Example.

11.b. 8 Illustrate uniform cost search and bi-directional search with example.

11.b. 9 Explain Alpha Beta Pruning with Example.

11.b. 10 Explain anyone gaming algorithm used in AI in detail. (Eg. Alpha-Beta,

min-max)

12.a. 1 Define knowledge representation in the context of artificial

intelligence. Discuss why it is essential for AI systems.

12.a. 2 Compare and contrast symbolic (logic-based) and sub-symbolic

(connectionist/neural network-based) approaches to knowledge
representation in AI. Provide examples of each.

12.a. 3 Explain the concept of ontologies in knowledge representation. How

are ontologies used in AI systems, and what benefits do they provide?

12.a. 4 Explain the concept of knowledge graphs and their role in knowledge
representation. How are knowledge graphs constructed, and what are
their applications in AI?

12.a. 5 Explain the concept of uncertainty in knowledge representation.

Discuss how uncertainty is handled in AI systems using probabilistic
methods such as Bayesian networks.

12.a. 6 Why we need knowledge representation in the context of artificial

intelligence. Explain in detail

12.a. 7 Define knowledge representation in the context of artificial

intelligence. Discuss why it is essential for AI systems.

12.a. 8 Explain the syntax and semantics of First Order Predicate Logic

12.a. 9 Define first-order predicate logic and explain its fundamental

components, including terms, predicates, quantifiers, and logical
connectives. Provide examples to illustrate each component.
12.a. 10 Compare and contrast first-order predicate logic with propositional
logic. Highlight the additional expressive power that first-order logic
offers and provide examples to illustrate the differences.

12.b. 1 Discuss the concept of satisfiability in propositional logic. Define what

it means for a formula to be satisfiable and explain how to determine
whether a formula is satisfiable using truth assignments.

12.b. 2 Discuss the concept of validity in propositional logic. Define what it

means for a formula to be valid and explain how validity is related to
logical consequence

12.b. 3 Define propositional logic and explain its fundamental components,

including propositions, logical connectives, and truth values. Provide
examples to illustrate each component.

12.b. 4 Discuss the applications of propositional logic in artificial intelligence

and related fields.

12.b. 5 Explain the different types of logical connectives in propositional logic

(e.g., conjunction, disjunction, implication, negation). Define their
truth tables and discuss their meanings in terms of truth-functional
semantics.

12.b. 6 Discuss the concept of satisfiability in propositional logic. Define what

it means for a formula to be satisfiable and explain how to determine
whether a formula is satisfiable using truth assignments.

12.b. 7 Discuss different algorithms used for automated planning in artificial

intelligence.

12.b. 8 Explain the concept of planning graphs in automated planning.

Describe how planning graphs are constructed and utilized in classical
planning algorithms like Graph Plan.

12.b. 9 Discuss the advantages of using planning graphs for representing and
reasoning about planning problems, including their ability to handle
complex domains and efficiently generate plans.

12.b. 10 Discuss how different planning algorithms can be integrated to

enhance planning efficiency and effectiveness.

13.a. 1 Illustrate different types of learning in detail.

13.a. 2 Why we need different forms of learning. Describe learning in detail.

13.a. 3 Describe in detail about 1) Supervised Learning

2)Unsupervised learnings.

13.a. 4 Discuss any two forms of learning with relevant real time example.
13.a. 5 Discuss some of the application of learning in Artificial intelligence.

13.a. 6 Whether learning in important for AI to perform well. Discuss and

write some learning algorithms.

13.a. 7 Define artificial neural networks and describe their basic architecture.

13.a. 8 Explain the roles of input layer, hidden layers, and output layer in an
ANN.

13.a. 9 Discuss the activation functions commonly used in neural networks

and their significance.

13.a. 10 Discuss the key components of an ANN architecture, including input

layer, hidden layers, output layer, and connections between neurons.

13.b. 1 Define the term "hypothesis" and explain its role in the scientific
method.

13.b. 2 Describe at least three criteria commonly used to evaluate hypotheses.

Provide examples of how these criteria can be applied in a scientific
investigation.

13.b. 3 Explain the importance of testability in hypothesis evaluation. Provide

examples of testable and non-testable hypotheses and discuss their
implications for scientific inquiry

13.b. 4 Discuss the concept of falsifiability in the context of hypothesis

evaluation. How does falsifiability distinguish scientific hypotheses
from non-scientific claims?

13.b. 5 Compare and contrast the strengths and limitations of quantitative

and qualitative methods for evaluating hypotheses. Provide examples
of situations where each approach may be more appropriate.

13.b. 6 Outline the steps involved in hypothesis testing using statistical

analysis. Explain how statistical significance is used to evaluate the
strength of evidence for or against a hypothesis.

13.b. 7 Describe the key assumptions underlying linear regression analysis.

13.b. 8 Discuss the implications of violating these assumptions on the validity

of regression results.

13.b. 9 Discuss various techniques for feature selection in linear regression

models, such as forward selection, backward elimination, and
stepwise regression.

13.b. 10 Compare the advantages and disadvantages of each technique in terms

of model performance and interpretability.

14.a. 1 Illustrate machine learning and its significance in modern technology

 and society.

14.a. 2 Explain the difference between traditional programming and machine

learning approaches.

14.a. 3 Discuss real-world applications where machine learning has provided

significant advantages over traditional methods.

14.a. 4 Provide examples of tasks and processes that can be automated using
machine learning algorithms.

14.a. 5 Elaborate how machine learning helps in handling complex and

uncertain data environments.

14.a. 6 Why we need machine learning? Explain with examples.

14.a. 7 Discuss in detail about Reinforcement learning

14.a. 8 Illustrate supervised learning in detail with some examples.

14.a. 9 Discuss in detail about Semi-Supervised learning

14.a. 10 Discuss Ensemble learning with appropriate example.

14.b. 1 Define abstraction and its significance in machine learning.

14.b. 2 Explain how abstraction allows machines to generalize from specific

examples to broader concepts

14.b. 3 Discuss how feature engineering and dimensionality reduction

techniques contribute to abstraction in machine learning models.

14.b. 4 Define knowledge representation and its importance in artificial

intelligence.

14.b. 5 Provide examples of knowledge representation techniques used in

expert systems, natural language processing, and other AI
applications.

14.b. 6 Discuss how knowledge learned in one task can be transferred to solve
related tasks.

14.b. 7 Illustrate precision, recall, and F1-score. Explain how each of these
metrics is calculated and discuss their significance in evaluating
classification models.

14.b. 8 What is accuracy in the context of classification? Discuss situations

where accuracy might not be the best metric for evaluating a
classification model and propose alternative evaluation metrics.

14.b. 9 Contrast the concepts of Type I error and Type II error in binary
classification. How do these errors relate to the precision and recall
 metrics?

14.b. 10 Describe the stages involved in the machine learning process, from
data collection to model deployment. Discuss the importance of each
stage and the potential challenges that may arise during the process.

15.a. 1 Cluster the following eight points (with (x, y) representing locations)
into three clusters using clustering algorithm K-means

A1(2, 10), A2(2, 5), A3(8, 4), A4(5, 8), A5(7, 5), A6(6, 4), A7(1, 2),
A8(4, 9)

Initial cluster centers are: A1(2, 10), A4(5, 8) and A7(1, 2).

15.a. 2 In the K-means clustering process, what is the role of the initial cluster
centers in determining the formation of clusters?
A1(2, 10), A2(2, 5), A3(8, 4), A4(5, 8), A5(7, 5), A6(6, 4), A7(1, 2),
A8(4, 9)

Initial cluster centers are: A1(2, 10), A4(5, 8) and A7(1, 2).

15.a. 3 Describe the iterative steps involved in the K-means algorithm for
clustering points into groups.

15.a. 4 How is the distance between points and cluster centers calculated in
the K-means algorithm, and what significance does it hold in the
clustering process?

15.a. 5 Explain the process of assigning points to clusters based on their

proximity to the cluster centers in the K-means algorithm.

15.a. 6 What is the criterion for updating the cluster centers during each
iteration of the K-means clustering algorithm?

15.a. 7 Discuss the convergence criteria used to determine when to stop

iterating in the K-means clustering process.

15.a. 8 How many iterations might be required for the K-means algorithm to
converge and produce stable cluster centers?

15.a. 9 What is the final clustering result obtained from applying the K-means
algorithm to the given set of points, starting with the specified initial
cluster centers?

15.a. 10 Cluster the following eight points (with (x, y) representing locations)
 into three clusters using clustering algorithm K-means

A1(2, 5), A2(2, 10), A3(8, 4), A4(5, 8), A5(7, 5), A6(6, 4), A7(1, 2),
A8(4, 9)

Initial cluster centers are: A1(2, 10), A4(5, 8) and A7(1, 2).

15.b. 1 What is multiple regression analysis, and how does it differ from
simple linear regression? Give a practical example.

15.b. 2 Describe the analysis of variance (ANOVA) in the context of multiple

regression. How is it used to assess the significance of predictors?

15.b. 3 Define information gain and entropy in the context of decision trees.
How are these measures used in attribute selection?

15.b. 4 Explain Occam's Razor and its significance in machine learning. How
does it relate to model complexity and generalization?

15.b. 5 How does ANOVA assess the significance of predictors in multiple

regression models? Describe the process of using ANOVA to evaluate
the individual contribution of predictors to the overall variance
explained by the model.

15.b. 6 Discuss the interpretation of the F-statistic in ANOVA for multiple

regression. What does a high or low F-value indicate about the
significance of the regression model?

15.b. 7 What is the role of Analysis of Variance (ANOVA) in multiple

regression analysis, and how does it contribute to understanding the
relationship between predictors and the response variable?

15.b. 8 Discuss the interpretation of the F-statistic in ANOVA for multiple

regression. What does a high or low F-value indicate about the
significance of the regression model?

15.b. 9 Illustrate with an example how ANOVA can be applied in multiple

regression analysis to compare the fit of different models and
determine the significance of predictors.

15.b. 10 Examine the interpretation of the F-statistic in the context of ANOVA

applied to multiple regression. What insights can be gained from
analyzing the F-value regarding the explanatory power of the
predictors in the regression model?

Part – C ( 1 x 15 = 15 Marks)
16.a. 1

Find the path from A to J using A* algorithm.

16.a. 2

Find Path from S to G using Best-First Search algorithm.

16.a. 3

Find Path from S to G using Best-First Search algorithm.

16.a. 4

Find Path from P to S using Best-First Search algorithm. Heuristic value given
inside each node.(For eg. P-(10))

16.a. 5

Find Path from S to H using Best-First Search algorithm.

16.a. 6

Find Path from S to I using Best-First Search algorithm.

16.a. 7 Explain the importance of continuous improvement in knowledge

management practices and technologies. Propose mechanisms for
gathering feedback from users, monitoring emerging trends in knowledge
management, and leveraging new technologies or best practices to enhance
the effectiveness of the knowledge management initiative over time.

16.a. 8 Conduct a needs assessment to identify specific challenges and

opportunities for knowledge management within the corporation. Consider
 factors such as organizational structure, cultural differences,
communication barriers, and existing knowledge-sharing practices.
Propose methods for gathering feedback and insights from employees at
all levels of the organization.

16.a. 9 Describe your approach to collecting social media data relevant to the
retail brand, considering factors such as platform selection, data sources,
and data acquisition methods. Discuss how you would preprocess the
collected data Kto prepare it for analysis, including steps such as data
cleaning, normalization, and feature extraction.

16.a. 10 Explain the concept of sentiment analysis and discuss different techniques
and algorithms that can be used to analyze the sentiment of social media
posts. Evaluate the suitability of supervised learning, unsupervised
learning, and hybrid approaches for sentiment analysis in the context of the
retail brand's data.

16.b. 1 “Marcus was a man. Marcus was a Pompeian. All Pompeians were
Romans. Caesar was a ruler. All Romans were either loyal to Caesar or
hated him. Everyone is loyal to someone. People only try to
assassinate rulers to whom they are not loyal. Marcus tried to
assassinate.Caesar”. Query: Does Marcus hate Caesar? Prove by
Resolution.

16.b. 2 Consider the following facts Team India Team Australia Final match
between India and Australia India scored 350 runs, Australia scored
350 runs India lost 5 wickets, Australia lost 7 wickets The team which
scored maximum runs, wins If the scores are same the team which lost
minimum wickets wins the match. Represent the facts in predicate,
convert to Clause form and prove by Resolution “India winsthe match”

16.b. 3 Consider the following sentences: Marcus was a man Marcus was a
Pompeian Marcus was born in 40 ADAll men are mortal All
Pompeian’s died the Volcano erupted in 79 ADNo mortal lives for
more than 150 years Convert them to Clause form. Answer the
question “Is Marcus dead now”. Clearly state the assumption made

16.b. 4 “The law says that it is a crime for an American to sell weapons to
hostile nations. The country Nono, an enemy of America, has some
missiles, and all of its missiles were sold to it by Colonel West, who is
American”. Prove that West is a criminal by Resolution.

16.b. 5 Discuss the role of mental events in shaping an individual's subjective

experiences and behavior. How do mental events such as thoughts,
perceptions, and emotions contribute to the richness of human
consciousness?

16.b. 6 Discuss the relationship between mental events and mental objects.
How do mental events interact with and manipulate mental objects
during cognitive processing? Provide a detailed explanation using
relevant cognitive theories and empirical evidence.
16.b. 7

16.b. 8

16.b. 9 Calculate the entropy of the dataset for each attribute and determine
which attribute is the best choice for the root node of the decision tree.

16.b. 10 Suppose a manufacturer of mechanical components is testing a new production

process that produces components with two possible defects: crack or
deformation.
The manufacturer has collected data on 500 components produced by the new
process, and has labeled each component as either defect-free, cracked, or
deformed. The data is summarized in the following table:

Also explain decision tree in detail.