Value Added Courses

Course Code Course Title

VAC (Odd Sem)

Applied Artificial Intelligence

VAC (Even Sem)

Applied Cloud Computing

FACULTY OF ENGINEERING AND TECHNOLOGY

Name of the Department Computer science and engineering
Name of the Program Bachelor of Technology
Course Code
Course Title Applied Artificial Intelligence
Academic Year 2023-2027
Semester
Number of Credits 2
Course Prerequisite A course on “Design and Analysis of Algorithms”
Course Synopsis To understand the concepts of state space representation,
exhaustive search, heuristic search together with the time and
space complexities
Course Outcomes:
At the end of the course students will be able to:
CO1 Possess the skill for representing knowledge using the appropriate technique for a given
problem.
CO2 Possess the ability to apply AI techniques to solve problems of game playing
CO3 Understand the concepts of computational intelligence.
CO4 Understand the Neural Networks and its usage.
Mapping of Course Outcomes (COs) to Program Outcomes (POs) & Program Specific
Outcomes:
COs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2 PS PS
O3 O4

CO1 3 2 1 1 1 1 1 1 _ _ 1 1 1 1 _ _

CO2 3 2 1 2 - 1 - 1 _ _ 1 1 1 1 _ _

CO3 3 2 1 1 1 - - 1 _ _ 1 1 1 1 _ _

CO4 3 2 1 2 _ _ _ _ _ _ _ 1 1 _ _ _

Ave 3 2 1 1.5 0.5 0.5 0.2 0.7 _ _ 0.7 1 1 0.75 _ _

rage 5 5 5
Course Content:
L T (Hours/Week) P (Hours/Week) Total
(Hours/W Hour/Week
eek)
2 - - 2
Unit Content and Competency
1 1.Explain Problem Solving by Search-I. (C2: Comprehension)
2. Define Intelligent Agents Problem Solving by Search –II: Problem-Solving Agents,
Searching for Solutions. (C1: Knowledge)
3. Recall the purpose and importance of Uninformed Search Strategies: Breadth-first
search, Uniform cost search, Depth-first search, Iterative deepening Depth-first search,
Bidirectional search. (C1: Knowledge)
4. Explain Informed (Heuristic) Search Strategies: Greedy best-first search, A* search,
Heuristic Functions, Beyond Classical Search: Hill-climbing search, Simulated
annealing search, Local Search in Continuous Spaces, Searching with Non-Deterministic
Actions, Searching wih Partial Observations, Online Search Agents and Unknown
Environment. (C2: Comprehension)
2 1. Analyze the Artificial Neural Networks-1– Introduction, neural network
representation, appropriate problems for neural network learning, perceptions,
multilayer networks and the back-propagation algorithm. (C4: Analysis)
 2. Analyze the Artificial Neural Networks-2- Remarks on the Back-Propagation
algorithm, An illustrative example: face recognition, advanced topics in artificial neural
networks. (C4: Analysis)
3.Evaluation Hypotheses – Motivation, estimation hypothesis accuracy, basics of
sampling theory, a general approach for deriving confidence intervals, difference in error
of two hypotheses, comparing learning algorithms. (C6: Evaluation)
3 1. Generalize the concept of Bayesian learning –Bayes theorem and concept learning.
(C5: Synthesis)
2. Explain the Maximum Likelihood and least squared error hypotheses, maximum
likelihood hypotheses for predicting probabilities, minimum description length
principle, Bayes optimal classifier, Gibs algorithm, Naïve Bayes classifier, an example:
learning to classify text, Bayesian belief networks, the EM algorithm.
(C2: Comprehension)
3. Describe the Computational learning theory, probably learning an approximately
correct hypothesis, sample complexity for finite hypothesis space, sample complexity
for infinite hypothesis spaces, the mistake bound model of learning.
(C2: Comprehension)
4. Recall the Instance-Based Learning- Introduction, k-nearest neighbour algorithm,
locally weighted regression, radial basis functions, case-based reasoning, remarks on
lazy and eager learning. (C1: Knowledge)
4 1. Explain the principles and mechanisms of Genetic Algorithms an illustrative example,
hypothesis space search, genetic programming, models of evolution and learning,
parallelizing genetic algorithms. (C2: Comprehension)
2. Analyze the Learning Sets of Rules, sequential covering algorithms, learning rule sets:
summary, learning First-Order rules, learning sets of First-Order rules: FOIL, Induction
as inverted deduction, inverting resolution. (C4: Analysis)
3. Describe Combining Inductive and Analytical Learning, inductive-analytical
approaches to learning, using prior knowledge to initialize the hypothesis.
(C1: Knowledge)

Teaching Learning Strategies and Contact Hours

Learning Strategies Contact Hours
Lecture 20
Practical -
Seminar/Journal Club 1
Small group discussion (SGD) 1
Self-directed learning (SDL) / Tutorial 1
Problem Based Learning (PBL) 1
Case/Project Based Learning (CBL) 2
Revision 4
Others If any: -
Total Number of Contact Hours 30

Assessment Methods:
Formative Summative
Multiple Choice Questions (MCQ) Mid Semester Examination 1
Quiz Mid Semester Examination 2
Seminars University Examination
Problem Based Learning (PBL) Short Answer Questions (SAQ)
Journal Club Long Answer Question (LAQ)

Mapping of Assessment with COs

Nature of Assessment CO1 CO2 CO3 CO4
Quiz ✓ ✓ ✓ ✓
Assignment / Presentation ✓ ✓ ✓ ✓
Unit test ✓ ✓ ✓ ✓
Mid Semester Examination 1 ✓ ✓ ✓ ✓
Mid Semester Examination 2 ✓ ✓ ✓ ✓
University Examination ✓ ✓ ✓ ✓
Feedback Process Student’s Feedback

References:
Textbooks:

1. Artificial Intelligence A Modern Approach, Third Edition, Stuart

Russell and Peter Norvig, Pearson Education.

References:

1. Artificial Intelligence, 3rd Edn, E. Rich and K.Knight (TMH)

2. Artificial Intelligence, 3rd Edn., Patrick Henny Winston, Pearson
Education.