11/19/2020 72 Course Name Knowledge Representation and Reasoning/Expert
System للادتسلااو ةفرعملا ليثمت
Course Information
Course Code
Course
No Credit
Unit
Lec Lab Tot Contact
Hours*
Lec Lab
ARTI 403
3
3 3*Every contact hour equals minimum 50 minutes
Track University
Requirement
College Requirement Program Requirement Core
Program
Artificial Intelligence (ARTI) Computer Science (CS)
Computer Information Systems (CIS) Cyber Security and Digital Forensics (CYS)
Level Level 8 Prerequisite
Course Description
The course is presented in a standard format of lectures, readings, problem sets. Students will be introduced to:
1. knowledge representation and reasoning techniques for knowledge-based systems.
2. knowledge-based solution for a given problem.
3. translate a natural language sentence into different knowledge representation forms.
4. Students will work in team on various assessments and projects.
Course Learning Outcomes (CLOs)
1.
Describe the knowledge representation and reasoning techniques for knowledge-based systems. (SO:0;PI:0.1).2.
Translate a natural language sentence into different knowledge representation forms. (SO:0;PI:0.1).3.
Design and implement a knowledge-based solution for a given problem. (SO:7;PI:7.2).4. Demonstrate a skill to work effectively in a team. (SO:5;PI:5.2).
Grading (Assessment Strategies)
Quiz(zes) 10% Assignments 20%
Project(s) Lab
Mid-term 20% Final 45%
Participation 5%
Textbook
Artificial Intelligence: Foundations of Computational Agents, 2nd edition, Cambridge University Press, 2017.
Reference Book
1. An Introduction to Description Logic. Franz Baader, Ian Horrocks, Carsten Lutz, Uli Sattler
2. Knowledge Representation and Reasoning (The Morgan Kaufmann Series in Artificial Intelligence) 1st Edition, ISBN-10:
9781558609327, ISBN-13: 978-1558609327, Year (June 2, 2004)
3. Frank van Harmelen, Vladimir Lifschitz, Bruce Porter, Handbook of Knowledge Representation (Foundations of Artificial Intelligence) 1st Edition, Elsevier Science; (January 22, 2008), ISBN-10: 0444522115, ISBN-13: 978-0444522115 Brief list of topics to be covered
PART 1: KR&R WITH PROPOSITIONAL AND FIRST ORDER LOGIC
Introduction to knowledge-based technologies and knowledge representation, Expert Systems, Propositional Logic as a simple knowledge representation language, Representing Knowledge in First Order Predicate Logic, Limitations of Propositional and First Order Predicate Logic
11/19/2020 73
Course Name Image Processing ةيمقرلا روصلا ةجلاعم
Course Information
Course Code Course No Credit Unit
Lec Lab Tot Contact Hours*
Lec Lab
ARTI 404 2 1 3 2 2
*Every contact hour equals minimum 50 minutes Track
University Requirement College Requirement Program Requirement Core
Program
Artificial Intelligence (ARTI) Computer Science (CS)
Computer Information Systems (CIS) Cyber Security and Digital Forensics (CYS)
Level Level 8 Prerequisite ARTI 402
Course Description
This course covers the investigation, creation, and manipulation of digital images by computer. The course consists of theoretical material introducing the mathematics of images and imaging. Topics include representation of two- dimensional data, time and frequency domain representations, filtering and enhancement, the Fourier transform, convolution, interpolation, color images. The student will become familiar with Image Enhancement, Image Restoration, Wavelets and Multiresolution Processing, Image Compression, Morphological Image Processing, Image Segmentation, Representation and Description, and Object Recognition.
Course Learning Outcomes (CLOs)
After successful completion of this course, students will be able to:
1. Explain how digital images are represented and manipulated in a computer. (SO:0; PI:0.2).
2. Write a program which implements fundamental image processing algorithms. (SO:7; PI:7.1).
3. Develop a theoretical foundation of fundamental Digital Image Processing concepts. (SO:7; PI:7.2).
4. Demonstrate a skill to work effectively in a team. (SO:5; PI:5.1).
5.
Communicate effectively both in oral and written form. (SO:3; PI:3.1).
Grading (Assessment Strategies)
Quiz(zes) 10% Assignments
Project(s) 10% Lab 15%
Mid-term 20% Final 40%
Participation 5%
Textbook
Rafael C. Gonzalez, Richard E. Woods, Digital Image Processing 4th Edition, Pearson; 4th Edition (March 30, 2017) ISBN- 10: 9780133356724, ISBN-13: 978-0133356724
Reference Book
Chris Solomon & Toby Breckon, Fundamentals of Digital Image Processing: A Practical Approach with Examples in MATLAB, Wiley-Blackwell Publisher, ISBN-10: 0470844736, ISBN-13: 978-0470844731
Brief list of topics to be covered
Course Introduction, Digital Image Fundamentals, Image Enhancement in Spatial Domain, Color Image Processing, Image Segmentation, Morphological Image Processing, Object Detection.
11/19/2020 74
Course Name Machine Learning للااملعتلا
Course Information
Course Code Course No Credit Unit
Lec Lab Tot Contact Hours*
Lec Lab
ARTI 406 3 3 3
*Every contact hour equals minimum 50 minutes Track
University Requirement College Requirement Program Requirement Core
Program
Artificial Intelligence (ARTI) Computer Science (CS)
Computer Information Systems (CIS) Cyber Security and Digital Forensics (CYS)
Level 8 Prerequisite ARTI 402
Course Description
Machine Learning is a science of getting machines to learn, more specifically, designing algorithms that allow computers to learn from empirical data. Machine Learning is about extracting useful information from large and complex datasets. ML has been described as the “next internet” due to the belief that it will revolutionize the way things are being done just as the internet revolutionized the way things are being done. It is the most important technology of this era as its applications cuts across all facets of human endeavors including but not limited to engineering, empirical science, autonomous driving, oil and energy, recommendation systems, speech recognition systems, etc. Machine Learning is a key to developing intelligent systems and analyze data in science and engineering. This course introduces the fundamental methods at the core of modern machine learning. It covers theoretical foundations as well as essential algorithms for supervised and unsupervised learning. Classes on theoretical and algorithmic aspects shall be complemented with practical sessions in form of assignments, practical homeworks and real-life course projects. Topics covered include: Algorithmic models of learning, machine learning framework, learning classifiers and regression models, regression and classifiers evaluations measures, decision trees, neural networks and its variants, support vector machines, Bayesian networks, nearest neighbor classifiers, ensemble and hybrid classifiers.
Computational learning theory, Dimensionality reduction, feature selection. Clustering, mixture models, k-means clustering, hierarchical clustering, distributional clustering. Reinforcement learning; pattern recognition.
Course Learning Outcomes (CLOs)
Upon successful completion of the course, students are expected to be able to:
1. Identify examples of classification and regression tasks, including the available input features and output to be predicted (SO:0; PI:0.1).
2. Describe the algorithmic basis of machine learning algorithms and concepts (SO:0; PI:0.1).
3. Explain implementation issues in learning algorithms and the evaluation of their performances (SO:7; PI:7.1).
4. Apply machine learning techniques and algorithms to real life problems (SO:7; PI:7.2).
5. Compare and contrast machine learning concepts and techniques (SO:6; PI:6.1).
6. Demonstrate ability to communicate effectively through scientific and technical documentation or presentation describing project activities and outcomes (SO:3; PI:3.1).
Grading (Assessment Strategies)
Quiz(zes) 10% Assignments 5
%
Project(s) 25% Lab
Mid-term 20% Final 35%
Participation 5%
Textbook
1. Introduction to Machine Learning, Third Edition 2014 by Ethem Alpaydin ISBN: 9780262028189, Publisher: MIT Press 2. Master Machine Learning Algorithms: Discover How They Work and Implement Them From Scratch by Jason Brownlee
Reference Book
- Bishop, C. (2006). Pattern Recognition and Machine Learning. Berlin: Springer-Verlag.
ISBN-13: 978-0387310732, ISBN-10: 0387310738
- Stephen Marsland, Machine Learning: An Algorithmic Perspective. http://www.amazon.com/Machine-Learning- Algorithmic-PerspectiveRecognition/dp/1420067184 .
- Tom Mitchell, Machine Learning, http://www.cs.cmu.edu/~tom/mlbook.html.
11/19/2020 75 Brief list of topics to be covered
Introduction to Machine Learning:
Definition and examples of broad variety of machine learning tasks, including classification, regression, etc.
Machine Learning: Concepts and Frameworks Algorithmic models of learning
Types of machine learning paradigms: supervised, unsupervised, semi supervised (with examples).
Supervised, unsupervised Inductive learning hypothesis
Learning theory (Bias-Variance trade-offs)
The over-fitting problem & techniques for detecting and managing the problem Machine learning framework.
Data preparation and pre-processing
Outliers (anomalies) detection or identification and their impact on various machine learning methods Missing values detection and treatment methods.
Learning classifiers and regression models regression and classifiers evaluations measures
Performance evaluation (such as cross-validation, direct partition into training and testing set (holdout method), ) Measuring classifier accuracy (accuracy, specificity, sensitivity, area under ROC curve, etc.)
Dimensionality reduction, feature selection/feature engineering, and curse of dimensionality.
A tour of selected ML Algorithms (I) Supervised machine learning
Simple learning algorithms, such as Naive Bayesian Classifier, decision trees, Nearest-neighbor algorithms Ensemble and hybrid machine learning techniques
Combining Multiple Learners -ML Ensembles/Hybrid & Types A tour of selected ML Algorithms (II) ANN, SVM, ELM etc.
Different machine Learning algorithms and techniques like Neural networks and its variants,
support vector machines, Bayesian networks, etc.
Unsupervised Learning and clustering
Clustering, mixture models, k-means clustering, hierarchical clustering, EM,
Further topics on ML (if time permits) e.g. introduction to Soft Computing and fuzzy modeling.
11/19/2020 76
Course Name Robotics and Intelligent Systems ةيكذلاةمظنلأاوتاتوبورلا
Course Information
Course Code Course No Credit Unit
Lec Lab Tot Contact Hours*
Lec Lab
ARTI 407 2 1 3 2 2
*Every contact hour equals minimum 50 minutes Track
University Requirement College Requirement Program Requirement Core
Program
Artificial Intelligence (ARTI) Computer Science (CS)
Computer Information Systems (CIS) Cyber Security and Digital Forensics (CYS)
Level 8 Prerequisite ARTI 401, ARTI 402
Course Description
This course focuses on designing, building, and programming autonomous robots using Lego Mindstorms EV3 kits. The course is presented in a standard format of lectures, readings, problem sets, and weekly labs to apply and enhance topics learnt in class. Students will also design and fabricate working robotic systems in a group-based term project.
Course Learning Outcomes (CLOs)
Upon successful completion of the course, students are expected to be able to:
1. List capabilities and limitations of today's state-of-the-art robot systems, including their sensors and the crucial sensor processing that informs those systems for their decision-making (SO:0; PI:0.2).
2. List the differences among robots' representations of their external environment, including their strengths and shortcomings (SO:0; PI:0.2).
3. Describe the uncertainties associated with common robot sensors and actuators; explain their impact on future courses of action (SO:0; PI:0.2).
4. Implement fundamental motion planning algorithms within a robot configuration space (SO:7; PI:7.1).
5. Design robotic and intelligent systems to undertake specific tasks through the integration of sensors, actuators, and software (SO:7; PI:7.2).
6. Analyze robotic and intelligent systems future courses of action (SO:7; PI:7.3).
7. Operate a robot to accomplish simple tasks using deliberative, reactive, and/or hybrid control architectures (SO:7; PI:7.1).
8. Work as a member of the team and take up leadership position when required (SO:5; PI:5.2).
9. Communicate effectively both in oral and written form (SO:3; PI:3.1).
Grading (Assessment Strategies)
Quiz(zes) 10% Assignments
Project(s) Lab
25%
Mid-term 20% Final 40%
Participation 5%
Textbook
The Robotics Primer, Maja J. Mataric, MIT Press, 2007, ISBN-13: 978-0262633543, ISBN-10: 9780262633543 Reference Book
Robot Modeling and Control, M. Spong, M. Vidyasagar, S. Hutchinson, ISBN: 978-0-471-64990-8, Wiley & Sons, 2005 Brief list of topics to be covered
Introduction to robotics; Locomotion and Manipulation; Sensors; Control (feedback, deliberative, reactive, hybrid, behavior- based control); Emergent behavior; Navigation; Mapping.
11/19/2020 77 Course Name Mathematical Foundations for AI عانطصلاا ءاكذلل ةيضايرلا سسلأا
Course Information
Course
Code Course No Credit Unit
Lec Lab Tot Contact Hours*
Lec Lab
MATH 403 3 3 3
*Every contact hour equals minimum 50 minutes Track
University Requirement College Requirement Program Requirement Core
Program
Artificial Intelligence (ARTI) Computer Science (CS)
Computer Information Systems (CIS) Cyber Security and Digital Forensics (CYS)
Level 8 Prerequisite MATH 402
Course Description
The purpose of this course is to present the fundamental concepts of multivariate calculus and optimization, which are required for rigorous studies in most areas of Computer Science including Artificial Intelligence. Topics included are: Functions of Several Variables, Limits and Continuity, Partial Differentiation and Gradients, Gradients of Vector-Valued Functions, Gradients of Matrices, Backpropagation and Automatic Differentiation, Higher-Order Derivatives, Linearization and Multivariate Taylor Series, Optimization Using Gradient Descent, Constrained Optimization and Lagrange Multipliers, Linear and Nonlinear programming.
Course Learning Outcomes (CLOs)
A
fter successful completion of this course, students will be able to:
1. Recognize properties of multivariate functions: Domain, codomain, and Graphs. (SO:0; PI:0.1).
2. Calculate the limits of multivariable functions and analyze their continuity and differentiability.
3. Evaluate partial derivatives, directional derivatives, and gradient vectors by using multivariate derivation rules, particularly the chain rule.
4. Derive the Taylor polynomial for single and multivariate functions and give its geometric interpretations.
5. Use mathematical rules to solve optimization problems, especially problems related to artificial intelligence. (SO:7;
PI:7.3).
6. Communicate effectively in the classroom. (SO:3; PI:3.2)
Grading (Assessment Strategies)
Quiz(zes) 20% Assignments 15%
Project(s) Lab
Mid-term 20% Final 40%
Participation 5%
Textbook
Marc Peter Deisenroth, A. Aldo Faisal, Cheng Soon Ong, Mathematics for Machine Learning, Cambridge University Press (April 23, 2020), ISBN- 978-1108455145.
Reference Book
James Stewart, Multivariable Calculus, Cengage Learning, 8th Edition (2016), ISBN- 1305266641 Brief list of topics to be covered
Functions of Several Variables, Limits and Continuity, Partial Differentiation and Gradients, Gradients of Vector-Valued Functions, Gradients of Matrices, Backpropagation and Automatic Differentiation, Higher-Order Derivatives, Linearization and Multivariate Taylor Series, Optimization Using Gradient Descent, Constrained Optimization and Lagrange Multipliers, Linear and Nonlinear programming.
11/19/2020 78
Course Name COOP Field Training نواعتلا ناديملابيردتلا
Course Information
Course
Code Course No Credit Unit
Lec Lab Tot Contact Hours*
Lec Lab
ARTI 444 3 3 3
*Every contact hour equals minimum 50 minutes Track
University Requirement College Requirement Program Requirement Core
Program
Artificial Intelligence (ARTI) Computer Science (CS)
Computer Information Systems (CIS) Cyber Security and Digital Forensics (CYS)
Level 8 Prerequisite 120 credit hours
Course Description
The Cooperative Field Training is a collaborative and structured practical training academic program at CCSIT between Imam Abdurrahman Bin Faisal University and employers to improve student's skills for employment upon graduation. The students who have completed at least 120 credit units are eligible to register for this course. The course duration is 12 weeks with 10 weeks on site training/practical work and 2 weeks for preparing the technical report & oral presentation. This training provides students complementary knowledge and training to deal with real-world problems in a professional environment. The students must join any organization and work under the supervision of 2 supervisors (1 faculty supervisor and 1 company/organization supervisor) to accomplish the training.
Course Learning Outcomes (CLOs)
Upon successful completion of the course, students are expected to be able to:
1. Describe the practical management process for the computer-based problem using Artificial Intelligence techniques (SO:0; PI:0.1).
2. Demonstrate the ability of getting acquainted with the applied work systems (SO:1; PI:1.1) 3. Develop practical skills through real-world applications (SO:7; PI:7.1).
4. Apply the courses & skills learned in the real-world application (SO:7; PI:7.1).
5. Judge and summarize the technical knowledge of the real-world environment (S0:2; PI2.2) 6. Participate effectively in a team (SO:5; PI:5.2).
7. Demonstrate a skill to work effectively in a team (SO:5; PI:5.2).
8. Communicate effectively in a variety of professional contexts (SO:4; PI:4.2).
9. Develop skills in oral presentation (SO:3; PI:3.2)
10. Write a comprehensive final report about the COOP task and experience (SO:3; PI:3.1)
Grading (Assessment Strategies)
Progress Report 15% Presentation 25%
Supervisor Evaluation 25% Lab
Mid-term Final Report 35%
Textbook
No prescribed textbook. However, IEEE templates and handouts will be given in classes.
• COOP Handbook (Year) Reference Book
• Not Applicable
Brief list of topics to be covered
• Not Applicable
11/19/2020 79 بساحلا نمأ