Artificial Intelligence

This course introduces students to the fundamental concepts, techniques, and tools used in artificial intelligence (AI). Topics include perception, reasoning, learning, and search algorithms (informed and uninformed). Students will gain skills in applying AI techniques to real-world problems.

This course explores the fundamental techniques and algorithms in Computer Vision, focusing on image processing, object detection, feature extraction, and pattern recognition. Students will learn to develop applications that enable computers to analyse and understand visual data from the real world.

This course introduces students to the fundamentals of Data Mining, focusing on techniques used to extract patterns and knowledge from large datasets. This course covers foundational data mining techniques such as association rule mining, clustering, and classification. Emphasis is placed on understanding the theoretical concepts behind these methods while applying them to practical scenarios. Students will explore tools and libraries used for data mining tasks and tackle projects that simulate realworld applications.

In this course the students will learn the Big Data platform and data governance to efficiently store and manage massive amounts of data. In addition, they will learn Big Data architecture, such as Hadoop, Map Reduce, Hbase, Big SQL and BigSheets. Students will use tools to capture, store and analyze structured and unstructured data.

This course introduces machine learning with a practical approach covering some of the most common learning models, algorithms, tools, and techniques. From supervised learning, it covers linear regression, logistic regression, and neural networks. From unsupervised learning, it covers Kmeans clustering, dimensionality reduction (principal component analysis), and anomaly detection. The course also discusses practical aspects considered when applying machine learning: data visualization, model selection, flow, model evaluation (testing, validation, overfitting, underfitting, bias, variance), regularization, and large-scale machine learning.

This course introduces machine learning with a practical approach covering some of the most common learning models, algorithms, tools, and techniques. From supervised learning, it covers linear regression, logistic regression, and neural networks. From unsupervised learning, it covers Kmeans clustering, dimensionality reduction (principal component analysis), and anomaly detection. The course also discusses practical aspects considered when applying machine learning: data visualization, model selection, flow, model evaluation (testing, validation, overfitting, underfitting, bias, variance), regularization, and large-scale machine learning.

This course explores the intersection of AI and human interaction, focusing on ensuring that artificial intelligence remains under human control. It emphasizes designing AI systems that meet human needs, operate transparently, deliver fair and equitable outcomes, and respect privacy.

This course introduces the principles of AI product management, focusing on developing, launching, and managing AI-driven products. Students will learn about the product lifecycle, from concept to market launch, while addressing key challenges such as user needs, ethics, and scalability in AI applications.

An internship is an important aspect of the AI curriculum that provides the student with hands-on experience and a good sense of what an actual job in an organization will be like. Students are required to join an IT department in a government or private organization for a summer period of at least 8 weeks in the last summer prior to student graduation. Students should be able to relate the internship experience to the knowledge that he or she has gained through the AI program courses.

This course focuses on the principles and applications of generative AI, including Generative Adversarial Networks (GANs) and Large Language Models (LLMs). In this course, students explore generative AI essentials, how to ethically use artificial intelligence, its implications for authorship, and what regulations for generative AI could look like. The course emphasizes both the theoretical foundations and practical applications of generative models in areas like content generation, and AI-driven design.

This course introduces Deep Reinforcement Learning (DRL), an emerging field combining deep learning and reinforcement learning to create intelligent agents that learn through trial and error. Students will learn the fundamentals of DRL, including core concepts, algorithms, and architectures used to build and train deep reinforcement learning models. The course also covers neural networks like CNNs and RNNs. Students will gain hands-on experience applying these techniques to real-world AI problems.

This course introduces students to expert systems in general and to rule-based systems in specific. Students learn how to build a rule-based expert system in a variety of application areas. They also learn advanced programming techniques which include topics of inexact reasoning, intelligent database management methods, and how to develop a community of expert systems. Students are also given the opportunity to demonstrate their understanding of the technology by building a rule-based expert system that addresses a real-world problem.

Game theory underpins several important recent advancements in AI such as multi-agent reinforcement learning and generative adversarial networks. Applications within computer science include the use of games in automated verification & model checking to model computing systems in an unknown and possibly adverse environment. In AI, games are applied to the analysis of multiagent systems. Recently, with the advent of the internet and e-commerce, many game theoretic questions in the interplay between economics & computing have received extensive attention. These include electronic auctions, & more generally mechanism design questions (inverse game theory) related to finding incentive structures for cooperation between independent entities on the internet. The course introduces students to the theory of non-cooperative games covering both its economic and algorithmic aspects. Topics that will be covered include equilibria, their existence and quality, equilibrium learning and computation.

This course introduces the concepts and techniques used in natural language processing (NLP), including text preprocessing, word embeddings, and language models. Students will explore applications such as sentiment analysis, machine translation, and chatbot development. Projects focus on using modern NLP libraries and frameworks to solve practical challenges.

This course focuses on integrating AI with robotics to develop intelligent autonomous systems. Students will study perception, decision-making, motion planning, and control using AI techniques like computer vision, reinforcement learning, and path planning algorithms. The course emphasizes practical applications in robotic systems, including autonomous navigation, object manipulation, and human-robot interaction.

This course is the first part of a two-semester senior-year capstone project for AI students. It aims to complement theoretical knowledge with in-depth, hands-on experience in AI project development. Students will work in teams on projects relevant to the AI sector, focusing on tasks such as requirement analysis, system architecture, design, implementation, testing, validation, project management, and maintenance. In this part, students will develop a project plan, provide a software requirement specification document, and create a high-level design for an AI-driven application or system.

Building on the groundwork laid in AI 495, this course focuses on implementing and completing the capstone project. Students will execute their proposed solutions, including AI model development and performance evaluation. Teams will utilize industry-standard tools and techniques to develop a functional prototype or system. The course culminates with a comprehensive project report and a formal presentation to faculty and industry stakeholders, demonstrating the ability to tackle complex, real-world problems with AI-enabled strategies. Emphasis is placed on teamwork, project management, and effective communication of findings. Student teams are required to deliver the executable code, submit a final report, and present and demonstrate their AI solution, showcasing its functionality and impact.