SWEG4112
Introduction to Machine Learning
College of Engineering
Department of Software Engineering
Course Outline
2nd Semester 2023/2024
SWEG4117 / Introduction to Artificial Intelligence Course Outline
Table of Contents
1. Course Information ................................................................................... 3
2. Instructor Information ................................................................................ 3
3. Course Overview ...................................................................................... 3
4. Course Objectives ..................................................................................... 4
5. Course Learning Outcomes ...................................................................... 4
6. Course Schedule and Instructional Method .............................................. 4
7. Assessment Tasks .................................................................................... 6
Feedback on Assessments ........................................................................... 7
8. Learning Resources .................................................................................. 7
Textbooks .................................................................................................. 7
References................................................................................................. 7
Online Resources ...................................................................................... 7
9. Grading Policy........................................................................................... 7
Pass requirements ..................................................................................... 8
10. Academic Integrity, Referencing and Plagiarism..................................... 8
Academic Integrity ..................................................................................... 8
Referencing................................................................................................ 8
Referencing Style....................................................................................... 8
Page 2 of 8 1st Semester 2023/2024 A/Y
SWEG4117 / Introduction to Artificial Intelligence Course Outline
1. Course Information
Course Code SWEG4112
Course Name Introduction to Machine Learning
Year/Semester Year IV/II
Academic Year 2023/2024
Pre-requisite(s) SWEG4117
Co-requisite(s) Nil
Credit Hour / ECTS 3/5
Course schedule Lecture [day | time] : [venue]
Tutorial [day | time] : [venue]
Laboratory [day | time] : [venue]
2. Instructor Information
Course Coordinator
Name Fedlu
E-mail
Telephone number ----------
<Optional>
Consultation hour
Course Instructor/s
Name Tesfaye Meshu Welde
E-mail [Link]@[Link]
Telephone number ----------
<Optional>
Consultation hour Monday 1:30 -3:30PM
Office (Block/Room) Bldg-64/R-403
3. Course Overview
Machine learning is an exciting and fast-moving field of Software Engineering with many
recent consumer applications (e.g., Microsoft Kinect, Google Translate, Iphone's Siri,
digital camera face detection, Netflix recommendations, Google news) and applications
within the sciences and medicine (e.g., predicting protein- protein interactions, species
modeling, detecting tumors, personalized medicine). This course introduces undergraduate
Software Engineering students to the field of machine learning. Students learn about the
Page 3 of 8 1st Semester 2023/2024 A/Y
SWEG4117 / Introduction to Artificial Intelligence Course Outline
theoretical foundations of machine learning and how to apply machine learning to solve
new problems. Assuming no prior knowledge in machine learning, the course focuses on
two major paradigms in machine learning which are supervised and unsupervised learning.
In supervised learning, we learn various methods for classification and regression.
Dimensionality reduction and clustering are discussed in the case of unsupervised
learning.
4. Course Objectives
Clearly explain what machine learning is and its overall goal
Compare the differences among Supervised, Unsupervised and
Reinforcement Learning approaches
Implement and execute basic machine learning algorithms.
Experiment with deep learning frameworks like PyTorch and TensorFlow
Engage in independent and lifelong learning with the broad
Applications area of machine Learning.
5. Course Learning Outcomes
Up on successful completion of this course, students shall be able to: Program
learning
outcome
s
CLO 1 Clearly explain what machine learning is and its overall goal PLO1
CLO 2 Compare the differences among Supervised, Unsupervised and PLO1
Reinforcement Learning approaches
CLO 3 Implement and execute basic machine learning algorithms. PLO5
CLO 4 Engage in independent and lifelong learning with the broad PLO9
Applications area of machine Learning.
Graduate Attributes
PLO1 Engineering Knowledge PLO7 Environment and sustainability
PLO2 Problem Analysis PLO8 Ethics
PLO3 Design/development of PLO9 Individual and teamwork
solutions
PLO4 Investigation PLO10 Communication
PLO5 Modern tool usage PLO11 Project management and
finance
PLO6 The engineer and PLO12 Lifelong learning
society
6. Course Schedule and Instructional Method
This course consists of 34 hours of class contact hours including lectures and
tutorials. You are expected to take an additional 86 hours of non class contact hours
to complete assessments, readings and exam preparation.
Page 4 of 8 1st Semester 2023/2024 A/Y
SWEG4117 / Introduction to Artificial Intelligence Course Outline
Week Topic [Module] Learning and CLO
Teaching Activity
Week 1 Chapter 1: Introduction to ML Lecture CLO1
Definition of Machine learning
Need of Machine learning
History of Machine learning
Machine learning Life cycle
Week 2 Lecture, Discussions CLO1,
Over view of the difference between
Supervised, Unsupervised , Reinforcement CLO2
Learning approaches
Introduction to Probability, Inference and
decision theory
Week 3 Chapter 2: Supervised Learning Lecture CLO 2
Linear and Logistic Regression,
regularization Compressed sensing, Linear
Classification, K-Nearest Neighbors
Week 4 Linear and Logistic Regression, Lecture CLO 2
regularization Compressed sensing, Linear
Classification, K-Nearest Neighbors
Week 5 Lecture CLO 2
Neural Networks Optimization, Stochastic
Optimization
Week 6 Lecture CLO 2
Deep Learning
Logistic Regression and Classification Error
Metrics:
Neural Networks & Back Propagation
Algorithm:
Week 7 Lab 1 : Introduction to Python, Jupyter Lab CLO 3
notebooks, Numpy, Scipy and Pandas for
numerical computation, Matplotlib and
Seaborn, Scikit Learn libraries, Tensor
flow, and Kera
Page 5 of 8 1st Semester 2023/2024 A/Y
SWEG4117 / Introduction to Artificial Intelligence Course Outline
Week 8 Test on Topics from Weeks 1-7 NA CLO 2
Week 9 Lab 2: linear Classification and Linear Lab CLO 3
Regression
Lab 3: Nonlinear classification, Kernel
methods SVMs
Week 10 Lecture, Discussions CLO 3
Lab 4: Non Linear Regression and
Classification + Deep Learning
Week 11 Chapter 3: Supervised Learning Module Lecture, Discussions CLO 3
Naïve Bayes
SVM and Kernels
Decision Trees:
Bagging
Random Forest Algorithm
Week 12 Chapter 4: Unsupervised Learning and Lecture, Discussions CLO 3
Clustering Methods:
K-Means Clustering
Hierarchical K-Means Clustering,
Building a K-Means Clustering Model,
Introduction to Markov Chains,
Coding unsupervised algorithm using scikit
package.
Week 13 Group Project Work on Searching Algorithms Tutorials, Discussions CLO 4
Week 14 Assessment of Project Work NA CLOs 2 & 4
7. Assessment Tasks
No Assessment Method Weight Week Due CLO Assessed
1 Project 20% Week 14 CLOs 2,3 & 4
2 Individual Assignment 10% Week 1 CLO1
3 Test 15% Week 8 CLOs 1 & 2
4 Group Assignment 5% Week 10 CLO3
5 Final Exam 50% Week 15-16 CLOs 1-4
Page 6 of 8 1st Semester 2023/2024 A/Y
SWEG4117 / Introduction to Artificial Intelligence Course Outline
Submission of Assessment Tasks
<Provide procedural advice for submitting work and indicate the policy on late submission, extension of
deadlines and special consideration.>
Late project reports/assignments will result in a grade reduction of 20% per 24 hours
late or portion thereof.
Feedback on Assessments
The return of any written exams including the final exam shall be corrected and return back to
students within a week. Assessing of the assignments for individuals and groups are based on
the instructions while they are given and their corrections are on the bases of using the
instructions as checking mechanism and the project evaluation is based on the work,
questions answering and deadline issues.
8. Learning Resources
Textbook
Pattern Recognition and Machine Learning, Christopher M. Bishop, 2006
References
1. Understanding Machine Learning: From Theory to Algorithms, Cambridge
University Press, Shai Shalev-Shwartz and Shai Ben-David, 2014
2. Bayesian Reasoning and Machine Learning, David Barber, 2014
3. Neural Networks and Deep Learning, Michael Nielsen, 2014
4. Deep Learning, Ian Goodfellow, Yoshua Bengio and Aaron Courville,
2016
5. Dive into Deep Learning, Aston Zhang, Zachary C. Lipton, Mu Li, and
Alexander J. Smola, 2022
9. Online Resources
[Link]
[Link] Policy
Grading of courses will be according to the university’s rules and regulation.
Examinations are graded and the letter grading system with corresponding points
shown below.
Page 7 of 8 1st Semester 2023/2024 A/Y
SWEG4117 / Introduction to Artificial Intelligence Course Outline
Marks Grade Grade Points
[90,100] A+ 4.00
[85,90) A 4.00
[80,85) A- 3.75
[75,80) B+ 3.50
[70,75) B 3.00
[65,70) B- 2.75
[60,65) C+ 2.50
[50,60) C 2.00
[50 F 0.00
Pass requirements
To pass this course a student must:
attempt all assessments.
achieve a minimum of 40% in the final exam.
9. Attendance
As per university guideline, a minimum 80% during lecture and 100% during practical
work sessions except for some unprecedented mishaps. Filure to fulfil this
requirement result in barring.
10. Academic Integrity, Referencing and Plagiarism
Academic Integrity
AASTU values academic integrity. Therefore, all students must understand the
meaning and consequences of cheating, plagiarism and other academic offenses
under the Code of Student Conduct and Disciplinary Procedures. Work submitted
must be your own, and others’ ideas should be appropriately acknowledged. If you
don’t follow these rules, plagiarism may be detected in your work using plagiarism
detection tool 'Turnitin'.
Referencing
Referencing is a way of acknowledging the sources of information that you use to
research your assignments. You need to provide a reference whenever you draw on
someone else's words, ideas or research. Not referencing other people's work can
constitute plagiarism.
Referencing Style
The University advises students to use the IEEE Referencing Style for written work
and oral presentations.
Page 8 of 8 1st Semester 2023/2024 A/Y