ECE 4420/6420 Knowledge Engineering

Revised on 08/26/2024

For the definitive and up-to-date course details, please refer to the syllabus on Canvas.

Description

TL; DR: Applied machine learning with Python for beginners.

The goal of this course is to ignite a passion for machine learning by demystifying its concepts and showcasing its transformative potential. Students will embark on a journey from understanding the basic principles of machine learning to mastering some of its most powerful algorithms. The course begins with an exploration of the history and wide-ranging applications of machine learning, setting the stage for a deeper dive into the mechanics of machine learning. Along the way, students will engage in hands-on assignments that demonstrate the real-world impact of machine learning. By the end of the course, students will not only have a strong foundational knowledge but also the confidence and curiosity to pursue further studies and innovations in this dynamic field.

Topics

  • Machine learning concepts and fundamentals
  • Data preprocessing
  • Supervised learning: k-nearest neighbors, support vector machine, linear regression, logistic regression, and so on
  • Unsupervised learning: k-means, hierarchical clustering, PCA, and so on
  • Ensemble learning: random forest, gradient boosting
  • Recommendation systems
  • Trustworthy machine learning

Prerequisite

  • Basic probability and statistics
    • Understand the basics of probabilities, gaussian distributions, mean, standard deviation, etc.
  • Basic calculus, linear algebra, etc.
    • Be comfortable taking derivatives and understanding matrix/vector notation and operations. (e.g., matrix multiplication).
  • Basic Python programming skills

Course Materials

No textbooks are required for this course. I recommend the following books for after-class reading:

Grading for ECE 4420

  • Homework
    • 5 programming assignments
  • In-class quizzes
  • Final project
  • Final exam
  • Attendance

Grading for ECE 6420

  • Homework
    • 5 programming assignments
  • In-class quizzes (with additional questions)
  • Final project
  • Final exam
  • Attendance

Late Policy

  • On the due date, the cutoff for on-time submission is 11:59 pm (East Time).
  • Late work is discounted 5% per calendar day late.
  • Late submissions are not accepted after seven calendar days past the original due date and are graded as zero immediately.