ESET 489

New course ESET 489 · Special Topics · Fall 2027

Artificial Intelligence with Engineering Applications

Learn how modern AI works, from the math behind machine learning to neural networks, transformers, and large language models, and use it to build an AI system for a real engineering problem.

See the 16-week roadmap Questions? Email the instructor
  • 3 credit hours
  • Undergraduate
  • Texas A&M University, ETID
  • Meeting times: TBD
Week 1 Foundations: the AI toolbox1/5 Python is the language of modern AI: almost every tool here is used from Python.
  • 16weeks, from linear algebra to LLMs
  • 6learning outcomes
  • 4exams, spread across the semester
  • 1team project, designed and demoed by you

About the course

This course introduces the principles and engineering applications of modern Artificial Intelligence (AI) and Machine Learning (ML). You will learn core machine learning methods, including regression, classification, clustering, dimensionality reduction, and anomaly detection, along with neural networks and deep learning architectures.

It also introduces modern generative AI: transformers and large language models, plus the high-level ideas behind VAEs, GANs, and diffusion models. The emphasis is on mathematical intuition, practical implementation with modern AI frameworks, engineering data pipelines, and real-world applications. Ethical and responsible AI (bias, fairness, privacy, and security) is discussed throughout.

You finish with a semester project: designing and evaluating an AI-based system for an engineering application.

What you will be able to do

  • Explain the core principles of AI and machine learning: key algorithms, neural networks, and ethical questions such as bias, fairness, privacy, and security.

  • Apply supervised learning (regression, classification, and ensemble methods) to analyze and solve engineering problems.

  • Apply unsupervised learning (clustering, dimensionality reduction, and anomaly detection) to explore and interpret complex datasets.

  • Design and train neural networks with modern AI frameworks, and understand training dynamics, evaluation, and optimization.

  • Explain generative AI and transformer models: attention, large language models, and the ideas behind VAEs, GANs, and diffusion models.

  • Design, build, and present an AI-based engineering project, with performance evaluation and responsible AI built in.

The 16-week roadmap

Each part builds on the one before it. Four exams are spread across the semester, and the project proposal is due in Week 8.

  1. Introduction

    1. Week 1Foundations of Artificial Intelligence, AI Tools, and Open Ecosystems

  2. Mathematical foundations for AI

    1. Week 2Linear Algebra I: Data as Vectors and Matrices
    2. Week 3Linear Algebra II and Calculus for Optimization
    3. Week 4Probability and Statistics for Learning

  3. Machine learning engineering

    1. Week 5Machine Learning Pipelines and Engineering

    Exam 1 after Week 5

  4. Supervised machine learning

    1. Week 6Supervised Machine Learning I
    2. Week 7Supervised Machine Learning II

  5. Unsupervised machine learning

    1. Week 8Clustering Methods and Association Rule Mining
    2. Week 9Dimensionality Reduction and Anomaly Detection

    Project proposal in Week 8

    Exam 2 after Week 8

  6. Deep learning

    1. Week 10Neural Network Fundamentals
    2. Week 11Neural Network Training and Optimization
    3. Week 12Deep Learning Architectures

    Exam 3 after Week 11

  7. Generative AI & transformers

    1. Week 13Transformers and Large Language Models I
    2. Week 14LLM Engineering II and Modern Generative AI Methods (VAEs, GANs, Diffusion Models)

    Exam 4 after Week 14

  8. Hands-on semester project

    1. Week 15Semester Project Presentations
    2. Week 16Semester Project Presentations

    Final project and presentation in Weeks 15 and 16

The semester project

In teams, you design, build, and evaluate an AI system for an engineering application. Some examples:

  • Predictive maintenance system
  • Intelligent sensor analytics
  • Computer vision application
  • AI-driven signal processing
  • LLM-powered engineering assistant
  • AI anomaly detection for networks

What you deliver

  1. ProposalWeek 8
  2. ImplementationAfter the proposal
  3. Technical reportWith the final project
  4. Presentation & demoWeeks 15–16

How you are graded

Grade weights: exams 45%, project 35%, attendance 10%, participation and discussion 10%
100%of your grade
  • Exams · 45%Four exams on the mathematical foundations, core machine learning, neural networks, generative models, and advanced AI techniques.
  • Project · 35%A semester-long project: design, implementation, evaluation, and a final presentation of results.
  • Attendance · 10%Lectures, in-class demonstrations, and discussions.
  • Participation & discussion · 10%Contributing to discussions, asking questions, and learning together.

Letter grades: A ≥ 90% · B 80–89.99% · C 70–79.99% · D 60–69.99% · F < 60%.

Reading

Class notes in Canvas, with these references:

  • Machine Learning Refined: Foundations, Algorithms, and Applications, 2nd ed., J. Watt, R. Borhani, A. K. Katsaggelos (Cambridge University Press)
  • Deep Learning: Foundations and Concepts, C. M. Bishop, H. Bishop (Springer, 2024)
  • Deep Learning, I. Goodfellow, Y. Bengio, A. Courville (MIT Press)
  • Generative Deep Learning: Teaching Machines to Paint, Write, Compose, and Play, 2nd ed., D. Foster (O’Reilly Media)

Plus selected chapters and recent research papers on GANs, diffusion models, transformers, and LLMs, and online tutorials for the hands-on sessions.

Instructor

Sabit Ekin

Sabit Ekin

Associate Professor, Engineering Technology and Industrial Distribution, Texas A&M University. Founding Director of the Generative AI Literacy Initiative.

Personal site · Other courses · Texas A&M profile

Join us in Fall 2027

Look for ESET 489 (Artificial Intelligence with Engineering Applications) when you register for Fall 2027. Questions about the course or whether it fits your plans? Just ask.

Email Sabit Ekin