Department Requirements - Artificial Intelligence
CCAI 320- AI Fundamentals
This course aims to establish basic elements of theory, practice and applications of artificial intelligence. The course covers main aspects of artificial intelligence such as artificial intelligence philosophy and perspectives, intelligent agents, solving problems by intelligent systems, intelligent search, knowledge representation, as well as its applications such as games and robotics.
CCAI 420 Artificial Neural Networks
This course introduces students to the use of neural networks. In this course they will be prepared for the advanced deep learning course. This course will cover basic neural network architectures and learning algorithms, for applications in pattern recognition, image processing, and computer vision. Three forms of learning will be introduced (i.e., supervised, unsupervised and reinforcement learning) and their applications.
CCAI 421 Machine Learning
The course mainly provides an introduction to the fundamental methods of machine learning. In this course the theoretical foundations as well as essential algorithms for supervised and unsupervised learning will be discussed. The topics included in this course are linear regression, perceptron, naïve Bayes, support vector machines, K means , DBscan, PCA, ICA, etc. Some real time scenarios will be discussed to visualize the application of Machine learning techniques.
CCAI 510 Senior Project I
This course is the first part of a sequence of two courses that constitute the graduation capstone project. In this course the students integrate the knowledge areas they learnt into a development based project in which they will deliver proposals, reports, and oral presentations. The course topics cover planning, analysis, and design phases of the projects.
CCAI 511 Parallel Computing
Make student understand time management and synchronization, distributed and parallel problem management...
CCAI 520 Senior Project II
This course is the second part of a sequence of two courses that constitute the BSc graduation capstone project. In this project, the student will continue the System/Research development of the project that started in CCAI510. The student will deliver oral presentations, progress reports, and a final report.
CCAI 521 Recommender Systems
This course builds upon the concepts of machine learning and introduces the students to applications of recommender systems. Recommender systems appear everywhere in our daily lives from Netflix movie recommendations to Amazon’s purchase recommendations. This course covers basic concepts of such recommender systems by covering content based and collaborative algorithms and their evaluation metrics. The associated lab work will enable the students to implement recommender systems using python. Thus, after successful completion of the course a student shall have both theoretical understanding and practical prowess to design and implement recommender systems.
CCAI513_DESIGN-PRINCIPLES OF ROBOTICS
This course is an introduction to the field of robotics. It covers the fundamentals of kinematics, dynamics, and control of robot manipulators, robotic vision, and sensing. The course deals with forward and inverse kinematics of serial chain manipulators, the manipulator Jacobian, force relations, dynamics, and control. It presents elementary principles on proximity, tactile, and force sensing, vision sensors, camera calibration, stereo construction, and motion detection. The course concludes with current applications of robotics in active perception, medical robotics, autonomous vehicles, and other areas.
CCAI 422 Image Processing
To learn and understand the fundamentals of digital image processing, and various image Transforms, Image Enhancement, restoration and analysis techniques and methods, image compression and Segmentation used in digital image processing.
CCCS312 Computer Organization and Architecture
In this course, the students understand the basic operation of computing hardware, and how it works. This course will introduce the fundamental concepts of computer architecture. The main contents of this course include computer abstraction, machine-level representation of data, computer arithmetic, CPU structure and functions, memory system organization and architecture, system input/output, multiprocessors, and digital logic.
CCAI 512 Natural Language Processing
This course will cover the foundations of natural language processing (NLP) from textual content processing to corpus understanding. It is designed for develop the syntactic and semantic concepts of NLP and introduce the computational techniques for analyzing and understanding textual content.
CCAI 410 Optimization_and_Regression
Concentrates on recognizing and solving convex optimization problems that arise in applications. Convex sets, functions, and optimization problems. Basics of convex analysis. Least-squares, linear and quadratic programs, semidefinite programming, minimax, extremal volume, and other problems. Linear regression, regularized regression and non-parametric regression. Students will learn to use optimality conditions, duality theory and interior-point methods in the formulation of optimization problems.
CCAI 411 Pattern Recognition
In this course, the basic methodologies, technologies, and algorithms of statistical pattern recognition from a variety of perspectives will be covered. The broader way the following topics will be covered during the course which include feature extraction, feature selection, Bayesian classifiers, neural networks, discriminative classifiers, clustering, performance evaluation, and fusion of models. The students have some exposure to the theoretical issues involved in pattern recognition system design such as the curse of dimensionality.
CCAI 530 Mixed Reality
This course gives students an opportunity to learn about “Mixed Reality” (MR) and a specific subset of MR referred to as “Augmented Reality” (AR). MR refers to computer systems that combine virtual content with the physical environment, allowing users to interact with these combined physical/virtual worlds.
CCAI 531 Speech Recognition
In this course, the basics of speech processing and some of its applications will be discussed. The course is mainly divided into two parts. First part of the course will cover the fundamentals of signal processing, speech production, time and frequency domain analysis techniques, acoustics and auditory perception. In second part, the main focus will be on several application areas including psychoacoustic compression schemes, speech recognition, music analysis and retrieval, and sound mixture organization.
CCAI 532 Computer Vision
This course provides an introduction to computer vision. The course will include fundamentals of image formation. The focus of the course is to learn and implement different methods that deal with images. The course will also provide application for computer vision.
CCAI 533 Multi-agent systems
This course is about the invention of autonomous agents and multi-agent technology which is one of the landmark events in the computer science community of the ‘90s. Agents are being espoused as a new model of computation for engineering information processing systems that are distributed, large, open and heterogeneous. Nowadays, an increasing number of software systems are being viewed in terms of autonomous agents in which the software components act more like "individuals" or agents, rather than just "parts". Agents are bringing together ideas from many disciplines: artificial intelligence, distributed processing, sociology, organizational and management science, but also biology, psychology, philosophy.
CCAI 534 Deep Learning
This course introduces students to the theory of neural networks including most widely used topologies and learning algorithms. In this course, student is introduced in main areas as learning methods, different types of advanced networks. This course will cover advanced neural network architectures and learning algorithms, for applications in pattern recognition, image processing, and computer vision. Three forms of learning will be introduced (i.e., supervised, unsupervised and reinforcement learning) and their applications.
CCAI 535 Advanced Artificial Intelligence
This is a course for students with some sophistication and considerable interest in exploring methods of designing and using algorithms useful for finding adequate answers to combinatorial large problems that require largely symbolic rather than numeric computing. It will be assumed that students are highly proficient in one or more high level computer languages and either are or will be able to function in functional and descriptive languages such as LISP and PROLOG. The goal of the course will be to study, analyze and critique basic and current research papers and to engage in artificial intelligence projects and experiments either alone or in small groups. Topics of study will include artificial intelligence environments, tools and expert systems building. Class participation will be encouraged for the review of the more recent AI literature.
CCAI 536 ETHICS FOR AI
This course start by describe the impact of rapid development of technologies on human society. It discusses professional ethics and its guideline for computer professional, Intellectual property rights, fair use, software protection and open source software. Elaborate the privacy issue and information disclosures, hacking, malware, cyber crime and attack and online voting. The course provides the details about the professional ethics in organization, software engineering code of ethics, failure and error in computer systems. It covers various example scenarios as practical exercises.
7/25/2019 10:55:22 AM