We will discuss topics including the fundamental principles of quantum mechanics as they apply to computation, quantum information theory concepts such as qubits, quantum gates, parameterized quantum circuits, and data encoding strategies. We will explore and implement Quantum Machine Learning algorithms, including Quantum Neural Networks trained as classifiers, Variational Quantum Eigensolvers for optimization, and the Quantum Approximate Optimization Algorithm. In this class, we aim to understand the opportunities and challenges at the intersection of quantum computing and machine learning, and we will gain hands-on experience implementing quantum machine learning algorithms using both quantum simulators and real quantum devices.
- Who should attend? This class is intended to be self-contained and is oriented toward people from all STEM disciplines who are interested in learning and discussing this exciting intersection of quantum computing and machine learning. To have a head start in this class, previous knowledge of Python and Linear Algebra would be beneficial, you can contact Dr. Daniel Sierra-Sosa (sierrasosa@cua.edu) if you need some study material.
Evolutionary Artificial Intelligence – CSC 448/548
Artificial Intelligence systems are increasingly expected to adapt, learn, and improve in dynamic environments. Evolutionary Artificial Intelligence (EAI) explores computational approaches inspired by natural evolution to design intelligent systems capable of adaptation, self-improvement, and robust decision-making. By combining evolutionary computation with modern AI methods, EAI enables the development of hybrid systems that integrate learning, reasoning, and optimization.
In this course, students will study the principles and techniques for building adaptive intelligent systems. Topics include evolutionary algorithms, genetic programming, neuroevolution, hybrid AI architectures, adaptive decision systems, and system-level design of intelligent agents. Students will also explore how evolutionary methods can be combined with modern machine learning and AI technologies to create systems that improve their performance over time.
Throughout the semester, students will design and implement an adaptive AI system that integrates multiple intelligence mechanisms, such as evolutionary search, neural learning, fuzzy reasoning, or optimization. The course emphasizes hands-on implementation and experimentation, allowing students to gain experience building intelligent systems capable of adapting to complex environments.
- Who should attend? This course is intended for senior undergraduate and graduate students interested in artificial intelligence, machine learning, adaptive systems, and intelligent system design. Students from computer science, engineering, and related STEM disciplines are encouraged to enroll. Prior programming experience is required, and prior coursework in Artificial Intelligence or Machine Learning is recommended. Students interested in research or advanced AI system development will particularly benefit from this course.
Artificial Intelligence of Things – CSC/AI/EE 449–549
The rapid growth of the Internet of Things (IoT) is transforming traditional sensing systems into large-scale intelligent infrastructures. In recent years, significant progress has been made in embedding artificial intelligence directly into edge devices, enabling systems that can sense, analyze, and respond to their environments in real time. This paradigm, known as the Artificial Intelligence of Things (AIoT), combines IoT connectivity with machine learning and edge computing to create intelligent, autonomous systems. AIoT technologies are increasingly used across many domains, including healthcare monitoring, smart cities, industrial automation, environmental sensing, and intelligent robotics. In this course, we will explore the fundamental principles of AIoT systems, including sensor data acquisition, embedded machine learning, and edge-based inference. Topics include TinyML for microcontrollers, data collection and preprocessing from embedded sensors, model design and training using Python and PyTorch, and model optimization and deployment using TensorFlow Lite for Microcontrollers. Students will learn how to build complete AIoT pipelines—from sensor data acquisition to machine learning model development and deployment on resource-constrained embedded hardware. Through hands-on projects, students will design and implement AIoT applications using microcontroller platforms such as the Arduino Nano 33 BLE Sense, integrating sensors, signal processing, machine learning models, and real-time inference. The course aims to provide both conceptual understanding and practical experience in building intelligent edge systems, and to explore the opportunities and challenges associated with deploying AI models in the real world embedded environments.
- Who should attend? This course is intended to be accessible to students from Computer Science, Electrical Engineering, Artificial Intelligence, and Data Analytics, as well as other STEM disciplines interested in intelligent sensing and edge AI systems. Students will gain practical experience in building AI-enabled IoT systems and understanding the design trade-offs of deploying machine learning models on resource-constrained devices. To benefit fully from this course, students should have prior experience with Python programming and basic machine learning concepts. Familiarity with linear algebra and introductory embedded systems is helpful but not strictly required. Students interested in learning about intelligent sensing, TinyML, and edge AI technologies are encouraged to enroll.