B.S./M.Eng. Graduate Courses for ECE
All courses listed below are offered both online and in-person.
ENAI 601 -- Numerical Methods for Engineering AI (3 credits): Covers the fundamentals of optimization, from formulating a mathematical optimization problem from a problem description, to solving a mathematical optimization problem using numerical algorithms in optimization software, with an emphasis on convex optimization. The main topics include: linear algebra overview; convex sets and convex functions; convex optimization; duality theory and optimality criteria, Karush-Kuhn-Tucker conditions; reinforcement learning; unconstrained optimization algorithms: gradient method, Newton's method, quasi-Newton methods; constrained optimization algorithms: conditional gradient method, gradient projection method, alternating direction method of multipliers, interior point method, primal-dual method; stochastic gradient descent; distributed optimization; global search algorithms. Students will acquire not only theoretical knowledge of optimization, but also hands-on experience with optimization methods and software through assignments and a project.
*Credit only granted for ENAI601 or ENEE464.
ENAI 602 -- Foundations of Machine Learning for Engineering AI (3 credits): Provides a foundational treatment of modern machine learning at the masters level, complemented with comprehensive projects that involve implementing the state-of-the-art machine learning algorithms on several datasets. The course topics are divided into 3 categories: 1) Classics of learning, including Bayesian decision theory, maximum likelihood estimation, Fisher's discriminant analysis, nearest neighbor classification, and support vector machines, clustering and dimensionality reduction, 2) Modern approaches to learning, including neural networks, deep learning networks, generative adversarial networks, autoencoders, and transformers, 3) Engineering perspectives on learning, including the effects of quantization and hardware implementation challenges, introduction to neuromorphic hardware and learning, and introduction to secure machine learning.
*Credit only granted for ENAI602 or ENEE436.
ENAI 603 -- Foundations of Data Science for Engineering AI (3 credits): This course provides a comprehensive introduction to data science, covering key techniques in data manipulation, cleaning, and exploratory data analysis (EDA) using Python and essential libraries. Students will learn how to work with specialized data types, including time series and geospatial data, and develop automated data workflows. The course also introduces predictive modeling, advanced applications and challenges, and interactive dashboard creation. Through hands-on exercises and a capstone project, students will gain practical experience in analyzing real-world datasets and effectively communicating their insights.
ENAI 604 -- Fair, Ethical and Sustainable Engineering AI (3 credits): With the growing use of machine learning and generative AI in high-stakes applications, ensuring these models are trustworthy, responsible, and sustainable is critical. This course explores five pillars of trustworthy AI: (i) explainability and interpretability to support human understanding, (ii) robustness against adversarial attacks and real-world uncertainty, (iii) ethical alignment with human values, (iv) privacy-preserving methods for confidentiality and compliance, and (v) sustainability through techniques like model compression and distillation. The course also introduces large language models (LLMs) and emerging approaches to enhance their trust, accountability, and sustainability.
ENAI 605 -- Generative Engineering AI (3 credits): Generative Engineering AI develops the student’s analytical and practical familiarity with, and understanding of, key generative engineering AI techniques and their application across select engineering disciplines. Students will develop proficiency in the mathematical foundations underlying current and future digital twin technologies, including variational filters for inference, generative models for prediction, and reinforcement learning for decision making, and will explore the potential for digital twins to drive innovation and solve complex engineering problems. Through lectures, hands-on assignments, and projects, students will develop knowledge and skills to harness the power of generative AI in advancing engineering research and practice.
ENAI 606 -- Large Language Models in Engineering AI (3 credits): This course introduces graduate engineering students to the foundations and frontiers of Large Language Models (LLMs), with an emphasis on both conceptual understanding and practical skills. We begin with core topics in natural language processing, tokenization, and language representation, then explore the transformer architecture, attention mechanisms, and the full LLM pipeline--from training to deployment. Students will examine key developments such as in-context learning, emergent capabilities, and prompt engineering, as well as multimodal extensions like Vision-Language Models (VLMs). Later weeks will address ethical considerations and recent trends in unified multimodal models. Through a mix of lectures, discussions, and hands-on assignments, students will be well-prepared to engage with cutting-edge research and real-world applications in generative AI.
ENPM 611 -- Software Engineering (3 credits): Software engineering concepts, methods, and practices important to both the theorist and the practitioner will be covered. The entire range of responsibilities expected of a software engineer are presented. The fundamental areas of requirements development, software design, programming languages, and testing are covered extensively. Sessions on supporting areas such as systems engineering, project management, and software estimation are also included.
*Credit only granted for ENPM611 or CMSC435.
ENPM 615 -- Embedded Systems (3 credits): Introduction to embedded systems design and evaluation: requirements, specification, architecture, hardware and software components, integration and performance evaluation. Topics include instruction sets, CPU, embedded computing platform, program design and analysis, operating systems, hardware accelators, multiprocessors, networks, and system analysis. Real-life embedded systems design examples will be used throughput the course to illustrate these concepts.
*Credit only granted for ENPM615 or ENEE452.
ENPM 673 -- Perception for Autonomous Robots (3 credits): This course offers a foundation in computer vision. Students will learn techniques and algorithms that can be used to solve an abundance of perception problems. This course is dedicated to anyone interested in giving their autonomous system (e.g., robot, autonomous driving car, or simply a smart camera) means to understand their surrounding world. Throughout the projects of this course students will gain hands-on experience in solving real-life problems such as lane detection for autonomous driving, computing velocities of moving objects, and building a 3D model of an object using 2D images from cameras. Moreover, students will gain experience with state-of-the-art tools such as programming using OpenCV, Python and introduction to Machine Learning using PyTorch.
Top