Description

This course gives a basic introduction to artificial intelligence (AI) and its applications. Students will study the core concepts and topics of AI including its history, solving problems, algorithmic and learning approaches. Through this course, students will learn how to apply AI methods to solve different problems. This course is an exploration of AI domain and its applications in modern lives.

Description

This course familiarizes students with theories, fundamental conceptions and their basic applications in probability, mathematics statistics, calculus and linear algebra. The course aims at helping students who have a major in computing, science, and other similar fields to develop skills that are useful in solving mathematical problems; for example, computing skills of statistics and probability, calculus and linear algebra  that are needed  as core subjects to proceed with the machine learning course.

Description

This course introduces students to the dominant programming languages for AI/ML and deep learning such as Python and R. It dives deeply into programming tools, libraries, and frameworks for building research projects. This includes reading and loading datasets, preprocessing data, understanding structure using statistical summaries and data visualization, data manipulation, and cleaning techniques. This course also guides students through learning and implementing popular ML and deep learning frameworks such as TensorFlow, Keras, and PyTorch for symbolic math, used to perform differential programming and linear algebra. Finally, this course will cover the fundamentals of the MATLAB.

Description

The course aims to familiarize students with the fundamental concepts of research and the importance of research and its methodologies, including theory of science and qualitative and quantitative methods. Also, the course aims to give students skills for understanding the structure of a research paper, critical reading of research paper, developing a research proposal for a master's project and writing a research manuscript.

Students will use these theoretical concepts of research to begin to critically review literature relevant to the field of artificial intelligent and its applications.

Description

This course introduces the fundamental concepts and functioning of machine learning. It covers theoretical foundations as well as essential algorithms for supervised and unsupervised learning. The practical part will focus on the application of machine learning to a range of real-world problems. The topics include  linear and logistic regression, naïve Bayes classifier, k-NN, decision tree, random forest, support vector machine, clustering, dimensionality reduction, and perceptron.

Description

This course introduces the students to computer vision throughout the continuum from image processing to computer vision, which can be broken up into low, mid and high-level processes, including Image Acquisition, Image Enhancement, Image Restoration, Morphological Processing, Image Segmentation, Representation & Description, and Object Recognition.

Description

Robotics and Embedded systems course covers the fundamentals of robotics including position, actuators, and robot coordinate system. Manipulator configuration including axis, angles, and frames are also investigated. Moreover, understanding forward and inverse kinematics as well as Denavit-Hartenberg convention. In the Embedded system part of the course, the following topics are covered: CPU architecture, instruction set, program development, and structured assembly processor.

Description

This course offers a broad introduction to neural networks and deep learning. It also explores the applications and theories relevant to problem solving using deep learning. The course applies deep learning algorithms to real-life problems in diverse domains such as computer vision, natural language processing, sequence modelling, and more. It covers neural networks, backpropagation, optimization (SGD, RMSprop, and Adam), autoencoders, convolutional neural networks, inception, residual networks, RNNs, LSTM, dropout, batch normalization, Xavier initialization, transfer learning, generative adversarial networks, and deep reinforcement learning.

Description

Advanced Robotics course investigates high-level robotic topics such as velocity kinematics, Jacobian derivation, singularities, performance matrices, trajectory planning, and PID control. In addition, topics like velocity sensing, control theory, path control, dynamics, and automation are also covered.  In the practical part of the course, simulation of manipulators and robot programing are investigated. 

Description

The Data Science course concentrates on techniques and methods needed to in the Data Science project life-cycle, which includes data collection, data management and data preprocessing, analysis, presentation, as well as operationalization. This class aims at giving students an introduction to all phases of the process of data process and using modern tools and real data; they will gain hands-on experience of the process. The course includes topics such as data formats, cleaning, and loading; data analysis, data governance, data storage in no-relational and relational store; topping up using cluster computing; and data visualization. They will also store and access various data through using suitable data management tools, database, control accessibility of data that is sensitive, and implement conversions of data in different formats. Finally, students will be capable of presenting the results of data science project using reports and visualizations to be used as a foundation of operationalization.

Description

This course provides an introduction to the field of computational linguistics, also called natural language processing (NLP) - the creation of computer programs that can understand and generate natural languages (such as English). We will use natural language understanding as a vehicle to introduce the three major subfields of NLP: syntax (which concerns itself with determining the structure of an utterance), semantics (which concerns itself with determining the explicit truth-functional meaning of a single utterance), and pragmatics (which concerns itself with deriving the context-dependent meaning of an utterance when it is used in a specific discourse context). The course will introduce both linguistic (knowledge-based) and statistical approaches to NLP, illustrate the use of NLP techniques and tools in a variety of application areas, and provide insight into many open research problems.

Description

This course studies the basic principles and practical algorithms used for information retrieval and text mining. It covers the tasks of indexing, searching, and recalling data, particularly text or other unstructured forms. The contents also include statistical characteristics of text, several important retrieval models, text categorization, recommendation system, clustering, information extraction, etc. The course emphasizes both the above applications and solid modeling techniques (e.g., probabilistic modeling) that can be extended for other applications.

Description

This course introduces key concepts and methods in bioinformatics. Emphasis will be put on efficient algorithms and techniques used in common applications for the analysis of genetic sequences. Topics covered: comparison and alignment of two or more sequences, indexing and searching of sequence databases, motif discovery, searching with sequence patterns, gene prediction as well as mapping and assembly of data from genome sequencing. Necessary basic knowledge of molecular biology will be communicated throughout.

Description

Self-driving cars, have rapidly become one of the most transformative technologies to emerge. They depend on Deep Learning algorithms and they create new opportunities in the mobility sector. This course is an introduction to the practice of deep learning through the applied theme of building a self-driving car. It is open to beginners and is designed for those who are new to machine learning, but it can also benefit advanced researchers in the field looking for a practical overview of deep learning methods and their application.

Description

In this course we explore data mining interdisciplinary field brings together techniques from databases, statistics, machine learning, and information retrieval. We will discuss the main data mining methods currently used, including data warehousing and data cleaning, clustering, classification, association rules mining, query flocks, text indexing and searching algorithms, how search engines rank pages, and recent techniques for web mining. Designing algorithms for these tasks is difficult because the input data sets are very large, and the tasks may be very complex. One of the main focuses in the field is the integration of these algorithms with relational databases and the mining of information from semi-structured data.

Description

This course discusses several aspects of parallel computing including parallel architectures, parallel algorithms, parallel programming languages and applications. Students will become familiar with different parallel computing approaches, software design, and programming environments. Also, students will learn how to design, analyze, and implement parallel algorithms for several kind of problems.

Description

This course provides students a solid introduction to the field of reinforcement learning. It also offers the fundamentals and practical applications of reinforcement learning and will cover the latest techniques used to create agents that can solve a variety of complex tasks, with applications ranging from gaming to finance to robotics. The topics include: Markov decision process, Policies, Value Functions & Bellman Equations, Learning and Planning with Tabular Methods, Dynamic programming, Monte Carlo, Temporal difference, SARSA, Q-learning, Function approximation, On-policy methods, Off-policy methods, Eligibility traces, Inverse Reinforcement Learning , Policy gradients, and Actor-Critic (A2C, A3C).

Description

The course covers what smart space are, exploring the contrasting visions of how they will transform our urban environments and lives, and considers whether smart cities can be sustainable. Then explains the role that latest and emerging smart networking technologies including Cloud Computing, Virtual Networking, big data analytics, 5G Mobile Networks, Mobile App Development, Unmanned Aerial Vehicles (UAVs), and Data and Network Security, which are creating new opportunities for business, education, research and many other aspects of our daily lives. technology can play in transforming cities and considers challenges such as data ownership, privacy and ethics.

Description

This course will present the advantages and challenges of telemedicine services. Special focus is placed on how communication, innovative technology, safety and efficiency are addressed through telemedicine. Also, the course covers Wearable technologies which can be innovative solutions for healthcare problems. The big data generated by wearable devices is both a challenge and opportunity for researchers who can apply more artificial intelligence (AI) techniques on these data in the future.

Description

To highlights the up to date issues in Artificial Intelligence field.  The main purpose of this course is to highlight and investigate selected "special topics" in Artificial Intelligence that are not covered in the other offered courses. Such topics might be interrelated to one or more AI disciplines.

Description

This course provides students with an opportunity to gather the knowledge and skills learned from the program coursework and conduct a research project with industrial applications. Students are expected to conduct a review of research literature and develop a set of hypotheses for a research project in AI. A research project explaining the hypotheses and alternative remedies to the problem must be submitted to the faculty supervisor at the end of the semester. Students are evaluated based on their research project and oral presentation. 

Description

The research outlined in the CSC624 proposal must be completed during this course. The final report of the research findings and recommendations should be submitted to the advisor and the results presented. The results should have direct practical applications and / or be available for publication in refereed publications. Students are evaluated based on the submitted research and oral presentation.

​Description

As part of student's academic program and the most valuable step to learn and experience knowledge from a full-time employment, an internship course gives a significant opportunity for students to engage with professional people and gain practical training experiment. Students will be able to apply theoretical concepts to practical or laboratory work.