Developing Curricula for Artificial Intelligence and Robotics (DeCAIR)

618535-EPP-1-2020-1-JO-EPPKA2-CBHE-JP

DeCAIR Course Syllabus Form

Author(s) Gheith Abandah

Author Organization Name(s) The University of Jordan

Work Package Number & Title Work Package 2: Development of new MSc and BSc programs in AIR

Activity Number & Title Activity 2.2: Designing and developing syllabi and content for the agreed upon
courses in the new programs
Work Package Leader Francesco Masulli, University of Genoa

Due Date of Delivery 1/2/2022 Project Month M14

Submission Date 23/11/2021 Project Month M10

Revision History
Version Date Author Description Action * Page(s)

1 18/7/2021 Gheith Abandah Original (base) document C 1-6

2 23/11/2021 Gheith Abandah Drop “AI” from the course name U 1-3
3 3/1/2022 Gheith Abandah Revision based on Peer Review 1 U 1-3
4 23/1/2022 Gheith Abandah Modifications for applying modern U 1-6
teaching methods in the Spring 2023 term
(*) Action: C = Creation, I = Insert, U = Update, R = Replace, D = Delete

Disclaimer
This project has been co-funded by the Erasmus+ Programme of the European Union.

You are free to share, copy and redistribute the material in any medium or format, as well as adapt, transform, and
build upon the material for any purpose, even commercially, provided that you give appropriate credit to the project
and the partnership, and indicate if any changes were made. You may do so in any reasonable manner, but not in
any way that suggests the partnership, or the European Commission endorses you or your use. You may not apply
legal terms or technological measures that legally restrict others from using the material in the same manner that
you did.

Copyright © DeCAIR Consortium, 2021-2024

Email: DeCAIR@ju.edu.jo
Project Website: http://DeCAIR.ju.edu.jo/

The European Commission's support for the production of this publication does not constitute an endorsement of the contents, which reflect
the views only of the authors, and the Commission cannot be held responsible for any use which may be made of the information contained
therein.

1
 Developing Curricula for Artificial Intelligence and Robotics (DeCAIR)
618535-EPP-1-2020-1-JO-EPPKA2-CBHE-JP

Course title Applied Machine Learning

Spring 2023

Course number 0907726

Credit hours (lecture and lab) 3 (3 + 0)

ECTS (weekly contact and self- 6 (3 + 3)

study load)

Prerequisites/co-requisites by None
course number and name

Prerequisites by topic (other Students are assumed to have good background in mathematics, particularly,
than the formal prerequisites calculus, linear algebra, statistics, and probability. Additionally, the students should
above) have good programming skills, preferably, using Python.

Level and type (compulsory, Masters’ compulsory course

elective)

Year of study and semester First year, first semester

Catalogue description This graduate course concentrates on the application of state-of-the-art AI and
machine learning algorithms for solving real-world problems. This course starts with
reviewing the Python programming language and its important related packages.
The covered topics include data preparation, training, evaluation, metrics,
supervised learning (regression, classification, neural networks, deep learning,
convolutional neural networks, and recurrent neural networks), basics of
unsupervised and reinforcement learning, and recommender systems. The course
uses active learning techniques to guarantee better engagement from the students.
Also, experts from the industry are invited to talk about the practical applications in
this domain. This course includes assignments and a practical term project.

Objectives 1. Introduce students to the techniques used in ML including data preparation,

training models, regression, classification, neural networks, and deep learning.
2. Introduce students to the practical techniques used in developing ML systems
including sample collection, training, and evaluation.
3. Introduce students to the programming techniques and libraries used in ML
(Python, Scikit-Learn, Keras, and TensorFlow).
4. Enable the students to gain practical skills in solving wide range of problems
using ML techniques.

The European Commission's support for the production of this publication does not constitute an endorsement of the contents, which reflect
the views only of the authors, and the Commission cannot be held responsible for any use which may be made of the information contained
therein.

2
 Developing Curricula for Artificial Intelligence and Robotics (DeCAIR)
618535-EPP-1-2020-1-JO-EPPKA2-CBHE-JP

Intended learning outcomes Upon successful completion of this course, students will be able to:
Program learning
No Intended learning Outcome (ILO)
outcome (PLO)*
1 Demonstrate a sound understanding of the main 1
techniques and algorithms in ML.
2 Solve a practical problem by developing an 3
appropriate ML system.
3 Communicate the development of a ML system 4
through a detailed technical report.
4 Use Python and its specialized libraries to develop 3
programs for solving ML problems.
(*) The PLOs are listed in the appendix
Teaching and learning Development of ILOs is promoted through the following teaching and learning
methods methods:

 Flipped Classroom: A type of blended learning, which aims to increase

student engagement and learning by having student complete readings at
home and work on live problem-solving during class time.
 Assignment Based Learning
 Project Based Learning
 The AI lab is open for the students to practice the practical aspects and
solve the programming homework assignments.
 The student attends the class presentations and participates in the
discussions and solving problems.
 The student joins the related online team/group and participates in its
discussions.
 The student studies the reference material, including books and videos.
 The student solves the programming assignments in machine learning.
 The student carries out a term project for solving a problem using ML
techniques.
 The student develops a professional report for the term report.

Learning material type Textbook, class handouts, some instructor keynotes, selected YouTube videos, and
access to a personal computer and the internet.

Resources and references A- Required book(s), assigned reading and audio-visuals:

1. Aurélien Géron, Hands-On Machine Learning with Scikit-Learn, Keras
and TensorFlow: Concepts: Tools, and Techniques to Build Intelligent
Systems, 3rd Edition, O’Reilly Media, Oct 2022.
2. François Chollet, Deep Learning with Python, 2nd Edition, Manning Pub.
Oct 2021.
3. Course web page at: http://www.abandah.com/gheith/?page_id=3028
B- Recommended book(s), material and media:
4. Alberto Artasanchez, Prateek Joshi, Artificial Intelligence with Python,
2nd Edition, Packt Publishing, Jan 2020.

The European Commission's support for the production of this publication does not constitute an endorsement of the contents, which reflect
the views only of the authors, and the Commission cannot be held responsible for any use which may be made of the information contained
therein.

3
 Developing Curricula for Artificial Intelligence and Robotics (DeCAIR)
618535-EPP-1-2020-1-JO-EPPKA2-CBHE-JP

5. Wes McKinney, Python for Data Analysis: Data Wrangling with Pandas,
NumPy, and Ipython, O’Reilly Media, 3rd Edition, Aug 2022.
6. K. Koutroumbas, S. Theodoridis, Pattern Recognition, 4th ed. Academic
Press, Oct 2008.
7. Richard O. Duda, Peter E. Hart and David G. Stork, Pattern Classification,
2nd ed. Wiley Interscience, 2001.

Topic outline and schedule

Week Topic ILO Resources
1-2 Introduction to ML 1 1
3-4 Python programming language 4 5
5-6 Data preparation and regression 1, 2, 4 1
7 Classification 1, 2 1
8 Training models 1 1
9 Classical techniques: SVM, decision trees and 1, 2 1
ensembles
10 Unsupervised learning and clustering 1, 2 1
11-12 Neural networks 1, 2 1
13 Deep neural networks 1 1, 2
14 Recurrent neural networks 1, 2 1
14 Reinforcement learning 1, 2 1
14 Recommendation systems 1, 2 4

Evaluation tools Opportunities to demonstrate achievement of the ILOs are provided through the
following assessment tools:
Assessment tool Mark Topic(s) Time
Homework assignments 10% Programming aspects W2-W14
Midterm exam 30% Theoretical and practical W4, W8,
aspects W12
Term project report 20% Practical and reposting W15
aspects
Final exam 40% All material W16
Total 100%

Student requirements The student should have a computer and internet connection.

Course policies A- Attendance policies:

 Attendance is required. Class attendance will be taken every class and the
university polices will be enforced in this regard.
B- Absences from exams and not submitting assignments on time:
 A makeup exam can be arranged for students with acceptable absence
causes.
 Assignments submitted late, but before announcing or discussing the

The European Commission's support for the production of this publication does not constitute an endorsement of the contents, which reflect
the views only of the authors, and the Commission cannot be held responsible for any use which may be made of the information contained
therein.

4
 Developing Curricula for Artificial Intelligence and Robotics (DeCAIR)
618535-EPP-1-2020-1-JO-EPPKA2-CBHE-JP

solution can be accepted with 25% penalty.

 The project report must be handed in in time.
C- Health and safety procedures:
 All health and safety procedures of the university and the school should be
followed.
D- Honesty policy regarding cheating, plagiarism, misbehavior:
 Open-book exams
 All submitted work must be of the submitting student.
 Other text or code must be properly quoted with clear source specification.
 Cheating will not be tolerated.
E- Available university services that support achievement in the course:
 Microsoft Teams team: Link
 AI Lab for practicing the practical aspects and solving the programming
assignments.
 Program announcements Facebook group: Link
Additional information None

The European Commission's support for the production of this publication does not constitute an endorsement of the contents, which reflect
the views only of the authors, and the Commission cannot be held responsible for any use which may be made of the information contained
therein.

5
 Developing Curricula for Artificial Intelligence and Robotics (DeCAIR)
618535-EPP-1-2020-1-JO-EPPKA2-CBHE-JP

Appendix

Learning Outcomes for the MSc in Artificial Intelligence and Robotics

Students who successfully complete the MSc in Artificial Intelligence and Robotics (AIR) will be able to:

1. Analyze and discuss the basic concepts, principles, techniques, and theories in AIR including artificial neural
networks, machine learning, data science, industrial and service robots, and intelligent and autonomous
robots.

2. Use critical thinking on concepts, principles, and practices related to AIR, and rigorously evaluate tools,
techniques, and outcomes using structured arguments based on subject knowledge.
3. Apply the methods and techniques of AIR in the design, analysis, and deployment of AIR solutions and
solving practical problems.

4. Show the ability to produce distinguished research work from problem inception to implementation, and
write quantitative and qualitative reports, and deliver them orally and in writing.

5. Demonstrate life-long learning, independent self-learning, and continuous professional development skills,
and apply new AIR knowledge.

6. Take responsibility, work effectively within a team, abide by professional ethics and societal values in
performing tasks and work, and apply work ethics and professional honor codes.

7. Use practical research methodologies to analyze and investigate issues related to AIR.

The European Commission's support for the production of this publication does not constitute an endorsement of the contents, which reflect
the views only of the authors, and the Commission cannot be held responsible for any use which may be made of the information contained
therein.