Semesters Taught
Fall 2026
Spring 2026
Fall 2025
Spring 2025
Fall 2024
This course focuses on identifying and characterizing computational problems for which artificial intelligence (AI) offers unique value.
Module 1: Optimization and evolutionary algorithms. The first module covers single- and multi-objective optimization problems for which exact methods may be computationally impractical. Students learn to formulate optimization problems and to design and evaluate solutions using metaheuristics, with an emphasis on evolutionary algorithms.
Module 2: Unsupervised representation learning. The second module explores linear and nonlinear dimensionality reduction, clustering, and topic modeling.
Module 3: Foundation models and generative AI. The third module introduces foundation models and generative AI, with an emphasis on large language models (LLMs). Students examine the principles underlying model pretraining, fine-tuning, and evaluation and gain practical experience building an LLM from scratch.
Integrative project. Students combine multiple approaches to solve complex computational problems and communicate their scientific findings effectively.
Credit hours: 3 lecture hours per week, with two 1.5-hour sessions.
Prerequisite: CS 4660.
Semesters Taught
Spring 2026
Spring 2025
This course provides a comprehensive introduction to the Functional Programming paradigm, emphasizing both its theoretical foundations and practical applications in contemporary software development. Core topics include pure functions, higher-order functions, immutable data, functional control structures, polymorphic functions, and lambda expressions. The course emphasizes evaluating functional programming trade-offs in terms of code conciseness, readability, and maintainability.
Prior experience with object-oriented and imperative programming is expected from students. Kotlin is the primary language of instruction due to its support for the topics mentioned above.
By the end of this course, students will be able to:
Design and implement functional software systems in Kotlin
Apply core and advanced functional programming principles
Reason about program structure, abstractions, and effects
Develop a non-trivial final project (server or mobile application)
Semesters Taught
Spring 2025
This course includes new topics, high-end techniques, and advanced algorithms and tools in Data Science, Machine Learning, and Deep Learning for various purposes, including prediction, detection, and decision-making. This course will also cover applications of data science in the industry and new technologies used by high-end companies and institutions.
Credit Hours: 3 lecture hours, once per week
Prerequisite: CS 4661
By the end of this course, students will be able to:
Apply advanced concepts, applications, and algorithms of data science, data analytics, data mining, and machine learning.
Apply and use statistical modeling and machine learning algorithms, including Artificial Neural Networks (ANN), Deep Neural Networks, Convolutional Neural Networks (CNN), RCNN, YOLO, Recurrent Neural Networks (RNN), Transformers, GAN, etc.
Apply high-end techniques and tools in Data Science, Machine Learning, and Deep Learning for various purposes including prediction, detection, and decision-making.
Understand the important applications of data science in real life and new technologies used by high-tech companies and institutions.
Apply and use the main algorithms and techniques for large-scale data analytics and machine learning.
Semesters Taught
Fall 2026
Fall 2025
Fall 2024
The proliferation of several programming languages in today’s technological evolution reflects the complexity of solving computation problems effectively. For this reason, learning a programming language extends beyond writing code. It involves understanding the principles and paradigms by which a program can be organized and executed. This course explores programming paradigms such as functional, concurrent/reactive, rule-based, aspect-oriented, and domain-specific programming. Students can enhance their problem-solving abilities by understanding these programming paradigms.
In this course, students will gain practical experience using programming languages such as C, Python, Kotlin, and Java to become familiar with imperative, functional, object-oriented, and concurrent programming. CS 3035 extended the knowledge and programming skills acquired in CS2013 - Programming with Data Structures and CS 2148 - Discrete Structures
Credit Hours: 2 lecture hour(s) 3 laboratory hour(s)
Prerequisite(s): CS 2013
with a grade of C or better
By the end of this course, you should expect to be able to:
Apply software programming principles to Identify, formulate, and solve complex programming problems.
Analyze problems and identify and define the computing requirements appropriate to their solutions.
Demonstrate a strong foundation in the different programming paradigms.
Demonstrate fluency in at least one programming language (i.e., C, Python, Kotlin, and Java) and acquaintance with at least three more.
Semesters Taught
Spring 2023
Fall 2022
In this course, we will cover the foundation of information visualization and learn how to transform data into visual representation to communicate effectively.
Throughout this course, students will learn how to design and evaluate data visualization based on the context. Also, in this course, we will determine the appropriate type of graph and apply the principles of human visual perception. We will implement custom visualization using the Python libraries: matplotlib and seaborn.
This course will cover the following topics: the value of information visualization, choosing effective visual displays (i.e., plot and chart), understanding the audience, and telling a story with data. Also, you will have the opportunity to apply the fundamentals by creating custom plots. Therefore, some experience with coding assignments successfully the assignments.
By the end of this course, the student should expect to be able to:
Understand information visualization fundamentals.
Design and evaluate visualizations.
Implement custom visualization using matplotlib and seaborn
python's packages.
Tell a story with data.