AIML Course File

PYDAH COLLEGE OF ENGINEERING
(Approved by AICTE, New Delhi and Affiliated to JNTUK, Kakinada)

YANAM ROAD, PATAVALA KAKINADA, 533461, E.G.Dist,
Department of Mechanical Engineering
Course File Enclosures
Year /Sem: III-II Name of the Subject: Artificial Intelligence

and Machine Learning
S.No Contents
1 Vision & Mission of College
2 Vision & Mission of Department
3 Course Objectives & Outcomes
4 Syllabus
5 Roll List
6 Class Time Tables
7 Subject Time Tables
8 Academic Callender
9 Lesson Plan
10 Actual Lesson Plan
11 Lecture Notes
12 Tutorial Classes
13 Question Bank
14 Assignment Questions
15 Mid Question Papers
16 Previous University Question Papers
17 Latest Previous Question Paper
18 Topics Beyond Syllabus
19 Internal Marks
20 Best and Worst Mid Answer Scripts
21 List of e-resources
22 Result Sheet published by university
23 Pass Percentage
24 Sample Assignment Sheet
25 Attainment Sheet
26 DVD with Video lectures, PPT etc.,
27 Course Completion Certificate
Pydah College of Engineering
Vision
 To equip the students to face both professional and technical competition across the globe with
complete confidence and the necessary skills.
Mission
 To impart value-based education by integrating holistic teaching and learning with innovative
practices.
 To make students compete in the changing global scenario to realize their dreams.
 To create a conducive environment for the students to acquire skills beyond the curriculum in
their interested areas.
Department Mechanical Engineering
Vision
To emerge as a cutting-edge knowledge hub in mechanical engineering by employing state-of-the-art

teaching-learning methodologies and research practices, fostering the development of professionals
with a penchant for creative thinking.
Mission
The department endeavors to impart a comprehensive education by instilling fundamental engineering

principles and fostering professional, innovative, and leadership skills among students through the
following activities:
1. Establishing a robust groundwork in mechanical and related engineering domains.
2. Creating a nurturing environment that enhances the joy and stimulation of learning.
3. Designing and constructing engineering systems tailored to meet specific requirements.
4. Cultivating creativity while honing communication and entrepreneurial abilities.
5. Instilling awareness of societal and professional responsibilities, ethical considerations, and the
imperative of lifelong learning.
6. Addressing current industry challenges and advancing research initiatives.

Course Objectives & Outcomes

Course objectives:
1) To understand the basic concepts of artificial intelligence, neural networks and genetic
algorithms.
2) To understand the principles of knowledge representation and reasoning.
3) To gain knowledge about bayesian and computational learning and machine learning.
4) To explore various machine learning techniques.
5) To understand the machine learning analytics and deep learning techniques
Outcomes:
1) Discuss basic concepts of artificial intelligence, neural networks and genetic algorithms.
2) Apply the principles of knowledge representation and reasoning.
3) Learn about Bayesian and computational learning and machine learning.
4) Utilize various machine learning techniques.
5) Apply the machine learning analytics and deep learning techniques.

Syllabus
UNIT– I:
Introduction: Definition of Artificial Intelligence, Evolution, Need, and applications in real world.
Intelligent Agents, Agents and environments; Good Behavior-The concept of rationality, the nature of
environments, structure of agents. Neural Networks and Genetic Algorithms: Neural network
representation, problems, perceptrons, multilayer networks and back propagation algorithms, Genetic
algorithms.
UNIT– II:
Knowledge–Representation and Reasoning: Logical Agents: Knowledge based agents, the Wumpus
world, logic. Patterns in Propositional Logic, Inference in First-Order Logic-Propositional vs first
order inference, unification and lifting
UNIT– III:
Bayesian and Computational Learning: Bayes theorem, concept learning, maximum likelihood,
minimum description length principle, Gibbs Algorithm, Naïve Bayes Classifier, Instance Based
Learning- K-Nearest neighbor learning Introduction to Machine Learning (ML): Definition, Evolution,
Need, applications of ML in industry and real world, classification; differences between supervised
and unsupervised learning paradigms.
UNIT– IV:
Basic Methods in Supervised Learning: Distance-based methods, Nearest-Neighbors, Decision

Trees, Support Vector Machines, Nonlinearity and Kernel Methods. Unsupervised Learning:
Clustering, K-means, Dimensionality Reduction, PCA and kernel.
UNIT– V:
Machine Learning Algorithm Analytics: Evaluating Machine Learning algorithms, Model, Selection,
Ensemble Methods (Boosting, Bagging, and Random Forests). Modeling Sequence/Time-Series Data
and Deep Learning: Deep generative models, Deep Boltzmann Machines, Deep auto-encoders,
Applications of Deep Networks.
TEXT BOOKS:
1) Stuart Russell and Peter Norvig, Artificial Intelligence: A Modern Approach, 2/e, Pearson
Education, 2010.
2) Tom M. Mitchell, Machine Learning, McGraw Hill, 2013.
3) Ethem Alpaydin, Introduction to Machine Learning (Adaptive Computation and Machine

Learning), The MIT Press, 2004.
REFERENCE BOOKS:
1) Elaine Rich, Kevin Knight and Shivashankar B. Nair, Artificial Intelligence, 3/e, McGraw Hill
Education, 2008.
2) Dan W. Patterson, Introduction to Artificial Intelligence and Expert Systems, PHI Learning, 2012.
3) T. Hastie, R. Tibshirani, J. H. Friedman, The Elements of Statistical Learning, 1/e, Springer, 2001.
4) Bishop, C. M., Pattern Recognition and Machine Learning, Springer, 2006.
5) M. Narasimha Murty, Introduction to Pattern Recognition and Machine Learning, World Scientific
Publishing Company, 2015.
Students Roll List
S.No Regd.no Name Of the Candidate
ATTILI VENKATA SRIRAM

1 206T1A0301
ELUGANTI BULLI KRISHNA
2 206T1A0302
ELUGANTI RAJU
3 206T1A0303
GURRAM VARUN KUMAR
4 206T1A0304
GUTHULA RAVI KIRAN
5 206T1A0305
KOYYA OMKAR
6 206T1A0306
MALLADI BHAGYA RAJU
7 206T1A0307
MARISA PRABHU KIRAN
8 206T1A0308
MEDA RAJESH
9 206T1A0309
REDDY AJAY
10 206T1A0311
216T5A0301 BANDARU SIMHACHALAM
11
216T5A0302 BODA KALYAN
12
216T5A0303 DADALA SANTHOSH KUMAR
13
216T5A0304 EERATHI VIJAYA NARAYANA
14
216T5A0305 GANDI SIDDU
15
216T5A0306 GEDALA SAI GANESH
16
216T5A0307 ILLA SATISH
17
216T5A0308 KODA RAVITEJA
18
216T5A0309 MALLADI GOVARAJU
19
216T5A0310 MUNTHA SRINU
20
216T5A0311 MYLA SATYA JAYA SANTOSH
21
216T5A0312 PEDDIREDDY JAGADEESH
22
216T5A0313 POLAMARASETTI RAVIKUMAR

23
216T5A0314 PUTREVU SRINIVASU
24
216T5A0315 SUNNAPU SATYA SAI
25
216T5A0316 THUMU SRIRAM
26
216T5A0317 THURPATI NARENDRA
27
216T5A0318 TUMMA UDAY KUMAR
28
216T5A0319 VESSAM NAGA VEERA PADMARAJU
29
YALLA NAGA GANGA SAI
216T5A0320
30 CHAKRADHAR
216T5A0321 YALLA SURYA KIRAN
31
216T5A0323 DEVARAKONDA VEERA VARAPRASAD
32
216T5A0324 EERLA AJAY
33
216T5A0325 GANJA DURGA PRASAD
34
216T5A0326 SANAPALA PRAVEEN KUMAR
35
216T5A0327 KATHURY VEERA VENKATA CHARAN
36
216T5A0328 AKKULA RAVI KUMAR
37
216T5A0329 ANUBOYINA RAMUDU
38
216T5A0330 UPPU KUMAR RAJ
39
216T5A0331 K PURNA BHHEMA CHANDRA
40
Signature of the HOD Signature of the principal

CLASS TIME TABLE


(Approves by AICTE, Newdelhi & Affiliated to SBTET, Andhra Pradesh)
6T
KAKINADA, Yanam Road, Patavala – 533461.
Department of mechanical engineering
B.TECH III/II (R-20) A.Y: 2022-23
Room No: 210 w.e.f: 10/01/2023
Hrs 1 2 3 4 5 6 7
Day/Time 09:15 - 10:05 10:05 - 10:55 10:55 - 11:05 11:05 - 11:55 11:55 - 12:45 12:45 - 01:4501:45 - 02:35
02:35 - 03:25 03:25 - 04:15
DMM-II HT IAIML AM M&M-LAB
MONDAY BREAK
HT IAIML-LAB AE R&IPR
TUESDAY
AE IAIML HT AE DMM-II AM CRT
WEDNESDAY
LUNCH
IAIML AE AM HT CRT DMM-II SPORTS
THURSDAY
BREAK
AM IAIML AM DMM-II CRT H.T-LAB
FRIDAY
IAIML AE DMM-II HT CAE&CAM Lab
SATURDAY
Signature of The Class Incharge Signature of The HOD
Signature Of The principal
SUBJECT TIME TABLE

Day/Time 09:15 - 10:05 10:05 - 10:55 10:55 - 11:05 11:05 - 11:55 11:55 - 12:45 12:45 - 01:45 01:45 - 02:3502:35 - 03:25
03:25 - 04:15
MONDAY BREAK AIML
TUESDAY
WEDNESDAY AIML
LUNCH
THURSDAY AIML
BREAK
FRIDAY AIML
SATURDAY AIML
ACADEMIC CALENDER
Lesson Plan
Uni Teaching No.of

Name of the Topic
t No Aid Classes
Definition of Artificial Intelligence, Evolution, Need, and Black Board

2
applications in real world & Chalk
Black Board
Intelligent Agents, Agents and environments 2
& Chalk
Good Behavior-The concept of rationality, the nature Black Board

1 2
of environments, structure of agents & PPT
Neural Networks and Genetic Algorithms: Neural network Black Board
2
representation & Chalk
Black Board
problems, perceptrons, multilayer networks 2
& Chalk
Black Board
Back propagation algorithms, Genetic algorithms. 2
& PPT
Black Board
Knowledge–Representation and Reasoning 2
& Chalk
Black Board
Logical Agents 2
& Chalk
2 Black Board
Knowledge based agents 2
& Chalk
Black Board
The Wumpus world, logic. 1
& Chalk
Black Board
Patterns in Propositional Logic 1
& PPT
Black Board
Inference in First-Order Logic 1
& Chalk
Black Board
Propositional vs first order inference 1
& Chalk
Black Board
Unification 1
& Chalk
Black Board
Lifting 1
& Chalk
Black Board
Bayesian and Computational Learning Bayes theorem , 2
& Chalk
concept learnin
Maximum likelihood, minimum description length principle, Black Board
2
Gibbs Algorithm, & Chalk
Naïve Bayes Classifier, Instance Based Learning- K-Nearest Black Board
3 2
neighbour learning & PPT
Introduction to Machine Learning (ML): Definition,
Black Board
Evolution, Need, applications of ML in industry and real 2
& PPT
world,
Black Board
2
Classification & Chalk
Differences between supervised and unsupervised learning Black Board

2
paradigms. & Chalk
Black Board
Basic Methods in Supervised Learning: Distance-based 2
& Chalk
method
Black Board
3
Nearest-Neighbors &PPT
Black Board
2
4 Decision Trees, Support Vector Machines & Chalk
Black Board
2
Nonlinearity and Kernel Methods. & Chalk
Black Board
2
Unsupervised Learning: Clustering, K-means & Chalk
Black Board
3
Dimensionality Reduction, PCA and kernel. & Chalk
Machine Learning Algorithm Analytics: Evaluating Machine Black Board
2
Learning algorithms & Chalk
Black Board
Model, Selection, Ensemble Methods (Boosting, Bagging, 3
& Chalk
5 and Random Forests).
Modeling Sequence/Time-Series Data and Deep Learning: Black Board
3
Deep generative models, Deep Boltzmann Machines & Chalk
Deep auto-encoders, Applications of Deep Networks. Black Board
2
& PPT
Total Hours 60
Lecture Notes
Question Bank
UNIT I
1. Define Artificial Intelligence and discuss its evolution. What are the primary needs that drive the
development of AI, and how is AI applied in real-world scenarios?
2. Explain the concept of intelligent agents in the context of AI. How do agents interact with their
environments, and what distinguishes good behavior in intelligent agents?
3. Elaborate on the concept of rationality in intelligent agents. How does it relate to decision-making,
and what factors influence the rational behavior of an agent? Discuss the nature and structure of
environments that intelligent agents operate within.
4. Provide an overview of neural networks in AI. Describe the representation of neural networks, the
role of perceptrons, and how multilayer networks with backpropagation algorithms contribute to
solving problems.
5. Explain the concept of genetic algorithms in AI. How do genetic algorithms use principles inspired
by natural selection to solve problems? Discuss their applications and advantages in the realm of
artificial intelligence.
UNIT II
1. How does a knowledge-based agent differ from other types of agents in AI, and what role does
knowledge play in decision-making for such agents?
2. Discuss the challenges and considerations involved in representing knowledge for intelligent agents
in real-world scenarios.
3. Explain the concept of logical reasoning in the Wumpus world. How does logical representation
contribute to problem-solving in this context?
4. In what ways can patterns be utilized in Propositional Logic, and how do they enhance the
expressiveness of logical statements?
5. Compare and contrast the strengths and weaknesses of propositional inference and first-order
inference in the realm of AI reasoning.
6. What are the key advantages of using first-order logic over propositional logic in AI applications?
Provide examples to illustrate the increased expressive power.
7. Describe the role of unification in first-order logic and its significance in resolving logical
statements and making inferences.
8. How does lifting address challenges in first-order logic, and how is it applied in AI systems to
improve knowledge representation?
9. Explore the potential impact of knowledge representation challenges on the performance and
decision-making capabilities of knowledge-based agents in AI.
10. Provide real-world examples that showcase the practical applications of effective knowledge
representation and reasoning in artificial intelligence systems. How does logical reasoning contribute
to solving complex problems in these instances?
UNIT III
1. Explain the fundamental principles of Bayes' theorem and its application in probabilistic reasoning
within machine learning.
2. Discuss the concept learning process in machine learning. What are the key challenges and
considerations when learning concepts from data?
3. Define and elaborate on the concept of maximum likelihood. How is maximum likelihood used for
parameter estimation in statistical models, especially in machine learning contexts?
4. Describe the Minimum Description Length (MDL) principle and its role in model selection. How
does MDL contribute to the learning process in machine learning algorithms?
5. What is the Gibbs algorithm, and how is it employed for sampling and inference in probabilistic
models within computational learning?
6. Provide an overview of the Naïve Bayes classifier. In what types of applications is the Naïve Bayes
classifier commonly used, and what are its strengths and limitations?
7. Explain the principles of Instance-Based Learning, focusing on K-Nearest Neighbour learning. How
does this approach make predictions based on instance similarity?
8. Define machine learning and discuss its evolution. What are the essential needs and applications of
machine learning in industry and real-world scenarios?
9. Explore the concept of classification in machine learning. How do algorithms in supervised learning
paradigms classify data into different categories, and what are the key considerations?
10. Differentiate between supervised and unsupervised learning. Provide examples illustrating
scenarios where each learning paradigm is commonly applied in machine learning.
UNIT IV
1. How do distance-based methods contribute to decision-making in machine learning, and what are
the key considerations in selecting an appropriate distance metric?
2. Discuss the role of Nearest-Neighbors in supervised learning. How does the choice of k impact the
performance of the algorithm, and in what scenarios is it particularly useful?
3. Explain the principles behind decision trees in supervised learning. How are decision trees
constructed, and what advantages do they offer in terms of interpretability?
4. What are the fundamental principles of Support Vector Machines (SVM) in supervised learning?
How does SVM handle classification tasks, and what makes it suitable for both linear and non-linear
relationships?
5. How does nonlinearity manifest in machine learning, and how do kernel methods contribute to
handling non-linear relationships in the data?
6. Define clustering in unsupervised learning. How do clustering algorithms group data points, and
what are the main challenges associated with this type of learning?
7. Discuss the workings of the K-Means algorithm in unsupervised learning. How does it partition data
into clusters, and what are the potential limitations of this approach?
8. What is the role of dimensionality reduction in unsupervised learning, and how does it impact the
efficiency and interpretability of machine learning models?
9. Explain the principles of Principal Component Analysis (PCA) and how it contributes to reducing
dimensionality in unsupervised learning.
10. How do kernel methods play a role in dimensionality reduction techniques in unsupervised
learning? Provide examples to illustrate their application and benefits.
UNIT V
1. How do machine learning algorithms typically get evaluated, and what are some key metrics used in
this evaluation process?
2. What factors should be considered when selecting a machine learning model for a specific task, and
how does model selection contribute to overall performance?
3. Explain the concept of ensemble methods in machine learning. How do boosting, bagging, and
random forests enhance the performance of models?
4. Discuss the principles of deep generative models in the context of machine learning. What are some
applications where these models are particularly effective?
5. What are Deep Boltzmann Machines, and how do they capture complex dependencies in data?
Provide examples of scenarios where they are applicable.
6. Elaborate on the role of deep auto-encoders in feature learning and dimensionality reduction. How
do they contribute to representing input data more efficiently?
7. Can you provide real-world examples where deep learning networks have demonstrated significant
success? Highlight applications in areas such as image recognition, natural language processing, or
recommendation systems.
8. What challenges are associated with modeling sequence or time-series data in machine learning, and
how do these challenges differ from traditional tabular data?
9. Discuss the benefits of using ensemble methods such as boosting, bagging, and random forests.
How do these techniques address issues like overfitting and improve overall model performance?
10. When applying deep learning models to practical problems, what are some considerations in terms
of data preparation, model training, and deployment?
Assignment Questions
UNIT I
1. Define Artificial Intelligence with respect to human intelligence.
b. Explain different applications of AI in various fields.
2. Explain about the evolution of AI.
b. Write about applications of AI in the real world.
3. Illustrate different types of Agents with their structures.
4. Explain about neural networks with examples.
5. Explain about backpropagation algorithms with examples.
6. Explain about genetic algorithms with examples.
UNIT II
1. Discuss various approaches and issues in knowledge representation. b. discuss various Problems in
representing knowledge.
i. What are frames, semantic nets? How do they differ from semantic nets?
ii. Explain semantic net with example.
2. Differentiate prepositional & predicate logic with example.
3. Compare inference in propositional logic with inference in first order logic.
4. What are the limitations of Predicate logic as a tool for Knowledge representation? Illustrate
through examples.
5. Explain about Extended semantic networks for KR.
UNIT III
1. Explain Probability and Bayes Theorem.
2. Define Uncertainty. How is it solved? What is Uncertainty Measure? Explain briefly.
3. Explain about Extended semantic networks for KR.
4. What is machine learning? Differentiate between supervised learning and

un supervised learning.
5. Describe case-based reasoning and learning.
6. What is machine learning? Explain about inductive and deductive learning.
7. What are the applications of Machine Learning in real life explain in detail.
8. Define Machine learning and explain in detail of evolution of ML.
UNIT-IV
1. Discuss Support vector machine in detail.
2. Why is the use of Nearest Neighbor classifiers problematic in high dimensional

input spaces.
3. Explain in brief about Decision trees in learning with an example?
4. What is K-Means Algorithm and explain with an example.
5. Explain about PCA and kernel
UNIT-V
1. What is Ensemble learning in Machine learning explain with an example?
2. Explain about Stacking Architecture with a neat sketch.
3. Distinguish between Bagging and Boosting.
4. what are the applications of Deep Networks in ML.
5. Explain about Boltzmann Machines and Deep auto-encoders in ML
Mid Question papers

III B.Tech II Semester I MID Examinations
INTRODUCTION TO ARTIFICIAL INTELLIGENCE

MECHANICAL ENGINEERING
Time : 90 Mins Max. Marks:30 Date:
S.No Note: Answer All Questions Marks BTL CO PO
Illustrate different types of Agents with their

1. 10 L2 CO1 PO1, PO 2
structures
Discuss various approaches and issues in PO1 , PO 2,

2. 10 L2 CO 2
knowledge representation. PO 3
Define Uncertainty. How is it solved? What is PO1, PO 2,

3. 10 L2 CO 3
Uncertainty Measure? Explain briefly. PO 3
III B.Tech II Semester I MID Examinations
INTRODUCTION TO ARTIFICIAL INTELLIGENCE

MECHANICAL ENGINEERING
Time : 90 Mins Max. Marks:30 Date:
S.No Note: Answer All Questions Marks BTL CO PO
Define Machine learning and explain in detail of

1. 10 L2 CO3 PO1, PO 2
evolution of ML.
Explain in brief about Decision trees in learning PO1 , PO 2,

2. 10 L2 CO 4
with an example? PO 3
What is Ensemble learning in Machine learning

explain with an example? PO1, PO 2,
3. 10 L2 CO 5
PO 3
Previous University Question Papers

Topics beyond Syllabus
1. Reinforcement Learning
2. Natural Language Processing (NLP)
3. Computer Vision:
4. Speech Recognition:
5. Data Mining
6. Ethical Considerations in AI
7. Robotics and AI
Internal Marks
Best and Worst Mid Answer Scripts

List of e-resources
1. https://www.youtube.com/watch?v=oV74Najm6Nc
2. https://www.youtube.com/watch?v=Pj0neYUp9Tc
3. https://www.youtube.com/watch?v=bjG3gS3Mh1U
4. https://www.ibm.com/topics/artificial-intelligence
5. https://cloud.google.com/learn/what-is-artificial-intelligence
Result Sheet published by university

Pass Percentage
S.No No.of Students Attended No.of Pass % Pass

1
Sign of Faculty Sign of HOD
Sample Assignment Sheet
Attainment Sheet
DVD with video lectures, PPT etc.,

Course Completion Certificate
I, , faculty in the department of Mechanical have taught
INTRODUCTION TO ARTIFICIAL INTELLIGENCE subject to students of III B.tech - II sem and
Mechanical during academic year 2022-23.I certified that I have completed FIVE units on ________
Signature of Faculty Signature of HOD
Date: Date:

AIML Course File

Uploaded by

Copyright:

Available Formats

AIML Course File

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

AIML Course File

Uploaded by

Copyright:

Available Formats

PYDAH COLLEGE OF ENGINEERING

(Approved by AICTE, New Delhi and Affiliated to JNTUK, Kakinada)

Department of Mechanical Engineering

Course File Enclosures

Year /Sem: III-II Name of the Subject: Artificial Intelligence

Pydah College of Engineering

Department Mechanical Engineering

To emerge as a cutting-edge knowledge hub in mechanical engineering by employing state-of-the-art

The department endeavors to impart a comprehensive education by instilling fundamental engineering

1. Establishing a robust groundwork in mechanical and related engineering domains.

3. Designing and constructing engineering systems tailored to meet specific requirements.

4. Cultivating creativity while honing communication and entrepreneurial abilities.

6. Addressing current industry challenges and advancing research initiatives.

Course Objectives & Outcomes

2) To understand the principles of knowledge representation and reasoning.

4) To explore various machine learning techniques.

5) To understand the machine learning analytics and deep learning techniques

2) Apply the principles of knowledge representation and reasoning.

3) Learn about Bayesian and computational learning and machine learning.

4) Utilize various machine learning techniques.

5) Apply the machine learning analytics and deep learning techniques.

Basic Methods in Supervised Learning: Distance-based methods, Nearest-Neighbors, Decision

2) Tom M. Mitchell, Machine Learning, McGraw Hill, 2013.

3) Ethem Alpaydin, Introduction to Machine Learning (Adaptive Computation and Machine

4) Bishop, C. M., Pattern Recognition and Machine Learning, Springer, 2006.

Students Roll List

S.No Regd.no Name Of the Candidate

ATTILI VENKATA SRIRAM

216T5A0313 POLAMARASETTI RAVIKUMAR

Signature of the HOD Signature of the principal

CLASS TIME TABLE

PYDAH COLLEGE OF ENGINEERING

Signature of The Class Incharge Signature of The HOD

Signature Of The principal

SUBJECT TIME TABLE

Uni Teaching No.of

Definition of Artificial Intelligence, Evolution, Need, and Black Board

Good Behavior-The concept of rationality, the nature Black Board

Differences between supervised and unsupervised learning Black Board

1. Define Artificial Intelligence with respect to human intelligence.

b. Explain different applications of AI in various fields.

2. Explain about the evolution of AI.

b. Write about applications of AI in the real world.

3. Illustrate different types of Agents with their structures.

4. Explain about neural networks with examples.

5. Explain about backpropagation algorithms with examples.

6. Explain about genetic algorithms with examples.

ii. Explain semantic net with example.

2. Differentiate prepositional & predicate logic with example.

3. Compare inference in propositional logic with inference in first order logic.

5. Explain about Extended semantic networks for KR.

1. Explain Probability and Bayes Theorem.

2. Define Uncertainty. How is it solved? What is Uncertainty Measure? Explain briefly.

3. Explain about Extended semantic networks for KR.

4. What is machine learning? Differentiate between supervised learning and

5. Describe case-based reasoning and learning.

6. What is machine learning? Explain about inductive and deductive learning.

8. Define Machine learning and explain in detail of evolution of ML.

1. Discuss Support vector machine in detail.

2. Why is the use of Nearest Neighbor classifiers problematic in high dimensional