CoEng AI Curriculum

Applied AI Fundamentals is designed for individuals with no prior programming or AI experience. This course offers a comprehensive introduction to the foundations of Artificial Intelligence, beginning with Python fundamentals and progressing to ML, including supervised and unsupervised learning techniques. Additionally, we explore deep learning and its practical applications tailored to various industries and disciplines. Through hands-on experience, participants will gain the skills and confidence to apply AI methodologies effectively in their respective fields.

Introduces foundational knowledge in data science, focusing on skills and concepts that will prepare students for further studies in artificial intelligence (AI) and machine learning (ML). Emphasizes practical data analysis, statistical concepts, and an understanding of algorithms preparing students to tackle real-world data science problems.

Introduces the basic concepts of artificial intelligence (AI). Topics include intelligent agents; heuristics, local and adversarial search; first-order logic and knowledge of representation and machine learning.

Introduces students to subjects in the broad field of evolutionary computing, including genetic algorithms, evolution strategies, evolutionary programming and genetic programming. Emphasis will be on the design, implementation, testing, debugging and verification of correct programs.

In-depth survey of basic and advanced concepts of machine learning. Topics include linear discrimination; supervised, unsupervised and semi-supervised learning; multilayer perceptrons; maximum-margin methods; Monte Carlo methods; and reinforcement learning.

Survey and application of techniques for classification, clustering and association rule mining. Covers rule-based, tree-based, statistical and regression approaches.

Covers how computers perceive the visual world of humans. Includes image processing, segmentation, boundary detection, as well as identifying, reconstructing, and modeling objects from images and videos.

Analysis, design and implementation of intelligent systems utilizing heuristics, local and adversarial search, first-order logic, knowledge representation techniques, and machine learning algorithms. Students will review published artificial intelligence research, write a research paper, and present research findings in a public forum.
Special Note: Not available for credit to students who have completed CSCE A405.

Broad coverage of the field of evolutionary computing, including genetic algorithms, evolution strategies, evolutionary programming and genetic programming. Emphasis will be on the design, implementation, testing, debugging and verification of correct programs. Graduate students will be required to complete a literature review of recent research in evolutionary computation, write the results of that review in a research summary paper and complete a presentation of these findings in a public forum.
Special Note: Not available for credit to students who have completed CSCE A412.

Topics include linear discrimination; supervised, unsupervised and semi-supervised learning; multilayer perceptron; maximum-margin methods; Monte Carlo simulation; and reinforcement learning. Students are required to implement a research project that applies machine learning technique(s) to a unique and original data set, or to develop a technique that combines or modifies one or more machine learning algorithms.
Special Note: Not available for credit to students who have completed CSCE A415.

Covers how computers perceive the visual world of humans. Includes image processing, segmentation, boundary detection, as well as identifying, reconstructing, and modeling objects from images and videos.

Covers how computers perceive the visual world of humans. Includes image processing, segmentation, boundary detection, as well as identifying, reconstructing, and modeling objects from images and videos.
Special Note: Not available for credit to students who have completed CSCE A485.