CSE 4102

Artificial Intelligence Lab, Course outline (OBE based Curriculum)

Part A
1. Course Code : CSE 4102
2. Course Title : Artificial Intelligence Lab
3. Course Type : Core Course
4. Level : Honors
5. Academic Session : Spring 2025
6. Course Instructor : Md. Hasibur Rahman
7. Pre-requisite :
8. Credit Value : 0.75
9. Contact Hours : 21
10. Total Marks : 100

11. Rationale of the course:

The Artificial Intelligence Lab is an immersive course designed to provide students with hands-on experience in
implementing and applying artificial intelligence techniques. Through a combination of lectures, practical
exercises, and project work, students will develop a deep understanding of AI concepts and gain proficiency in
programming AI algorithms. The course focuses on both theoretical foundations and practical implementation
aspects of AI, preparing students for real-world AI applications.

12. Course Learning Outcomes (CLOs) and Mapping of CLOs with Program Learning Outcomes (PLOs):
Program Learning Outcomes (PLOs):
PLO Area Program Outcomes
Engineering Apply the knowledge of mathematics, science, engineering fundamentals to the
PLO1
knowledge solution of complex problems of computer and information technology.
PLO2 Problem analysis Identify, formulate, research and analyze complex Computer Engineering problems.
Design solutions for complex computer engineering problems and design system
Design and
PLO 3 components or processes that meet the specified needs with technological
Development
concerns.
Conduct investigations of complex computer science and technology problems,
PLO4 Investigation
considering experimental design, data analysis and interpretation.
Create, select and apply appropriate techniques, resources and modern computer
PLO5 Modern tool usage
engineering and ICT tools.
Engineer and The engineer and society: Apply reasoning informed by contextual knowledge to
PLO6
Society develop the computer technologies for society benefits.
Understand the impact of professional computer Engineering solutions in societal
Environment and
PLO7 and environmental contexts and demonstrate the knowledge for sustainable
sustainability
development.
Apply ethical principles and commit to the professional ethics, responsibilities and
PLO8 Ethics
the norms of the engineering practice.
Individual work and Function effectively as an individual and as a member or leader of diverse teams
PLO9
teamwork and in multidisciplinary settings.
Communicate effectively about complex computer science and Engineering
PLO10 Communication activities with the engineering community and with society at large in both oral and
written.
Project Demonstrate knowledge and understanding of computer engineering and
PLO11 management and management principles and apply these to one’s work as a team member or a
finance leader to manage projects in multidisciplinary environments.
Recognize the need for and have the preparation and ability to engage in
PLO12 Life-long learning
independent, life-long learning in the broadest context of technological change.

1
 Course Learning Outcomes (CLOs):

By the end of this course, students will be able to:

Understand fundamental concepts and techniques in artificial intelligence, including machine learning and
CLO 1
data analysis.
Apply AI techniques to solve real-world problems in various domains, focusing on data-driven decision-
CLO 2
making.
CLO 4 Collaborate effectively in a team-based AI project environment, presenting solutions and findings clearly.

Mapping CLO with BNQF:

No. of CLOs BNQF Domain Blooms Domain PLO mapping

CLO1 F4 Cognitive PLO2, PLO5
CLO2 T1 Affective PLO4
CLO3 F6, T2 Psychomotor PLO9, PLO11

Marks Distribution on CLOs:

Continuous Assessment (40)
Total
CLOs Lab Performance Lab Reports Viva Final Exam (60)
(100)
(20) (10) (10)
CLO-1 5 - 5 20 30
CLO-2 10 5 5 20 40
CLO-3 5 5 N/A 20 30

Topics to be covered/ content of the course-

Corresp
Teaching Learning Assessment
Week Topic onding
Strategy Strategy
CLOs
1, 2 Introduction to Prolog Programming

Intended Learning Outcome:

At the end of the session, student should be able to:
• Give some simple examples of Prolog programs
• Discuss the three basic constructs in Prolog:
– Facts
Slide Presentation Class
– Rules
to motivate the Participation
– Queries
students, & and CLO1
• Explain other concepts, such as
Interactive performance
– the role of logic
discussion
– unification with the help of variables
• Write codes using
– terms
– atoms, and
– variables

2
3. Introduce PROLOG built in ability for performing
“Family trees relationship” & basic arithmetic.

Intended Learning Outcome:

Hands-on Lab
Formative
- Understand Prolog’s Built-in Predicates Sessions, Problem-
Assessment CLO1
Solving Activities,
Interactive Lecture
- Apply Prolog to Solve Family Tree Problems

- Utilize Prolog for Basic Arithmetic Operations

4. Solving real world problem using Prolog:

 Monkeys’ and Banana Problem
 Tower of Hanoi Interactive
 Farmer Crosses river puzzle Demonstration,
Presentation CLO1
 Water and Jug problem Guided Coding
Learning Outcomes: Sessions
Develop Problem-Solving Strategies in Prolog

5, 6. Introduction to data visualization and machine learning

libraries.
Learning Outcomes: Hands-on Lab
Exercises
Assignment CLO3
 Explore Machine Learning Libraries Project-Based
 Apply Basic Data Visualization and Machine Learning
Learning Techniques

7. Data Processing
Lecture with
Expected Learning Outcomes: Case Studies, Formative
Interactive Assessment CLO2
 Apply Data Cleaning Techniques Coding Sessions
 Perform Data Transformation and Integration

8. Supervised machine learning algorithms (Part-1)

 Linear, logistic regression, KNN

Lecture and Formative
Expected Learning Outcomes:
Discussion, and
CLO2
Guided Coding Summative
 Understand Supervised Learning Concepts Practice
 Implement Linear and Logistic Regression
 Apply K-Nearest Neighbors (KNN) Algorithm

9. Supervised ML algorithm (Part-2) Conceptual Class

Lecture, Participation
CLO3
 Support Vector Machine Comparative and
 Decision Tree Analysis performance

3
  Random Forest

Expected Learning Outcomes:

 Understand the Fundamentals of SVM

 Implement and Analyze Decision Trees
 Apply and Interpret Random Forest Models

10, Uniformed Search

11.
 BFS, DFS
 Alpha Beta Pruning Lecture with
Visual Aids, Formative
Expected Learning Outcomes: CLO2
Problem-Solving
Sessions
 Implement BFS and DFS Algorithms
 Apply Alpha-Beta Pruning in Game Trees

12. Lab Tests

Informed Search Class
Lecture with
 Greedy, A* Participation
Heuristic CLO2
and
Examples
performance

13. Unsupervised Machine Learning

 SOTA unsupervised algorithms Class

Case Study and
Participation
Project Work,
and CLO 2
Hands-on
performance
Practice

14. Artificial Neural Network

Class
Learning Outcomes: Lecture and
Participation
Understand the Structure and Function of ANNs Visualization,
and CLO3
Train and Evaluate Neural Networks Project-Based
performance
Apply ANNs to Real-World Problems Learning

Lab Final Examination

Md. Hasibur Rahman

Lecturer
Department of Computer Science and Engineering
Khwaja Yunus Ali University