Instructor: Berdakh Abibullaev, Ph.D.

Office hours: Tue, Thu, 15:00 - 16:00 pm and by appointment

Office location: 7e318

Email: [email protected]

Lecture time: Tue, Thu, 10:30 am - 11:45 am

Lecture Room: 3E.227

TA: Nurlan Kabdyshev

Email address: [email protected]

Office hours: by appointment

📜 Course Description

ROBT 407 introduces students to state-of-the-art analytical tools and methods used in machine learning. Topics covered include (semi)supervised and unsupervised learning, neural networks, deep learning, support vector machines, design of machine learning experiments, decision trees, linear discrimination, and kernel-based learning methods. The course also includes integrated term projects, utilizing Python-based machine learning packages such as scikit learn, Pytorch, Numpy, Scipy, Pandas, Matplotlib, and online databases.

🗝 Enrollment

Prerequisite(s): MATH 273 Linear Algebra with Applications, MATH 321 Probability (must be completed with a grade of "C-" or better) Recommended Preparation: Linear Algebra, Probability, Optimization, Numerical Python

📚 Readings

Required Texts

📚 Course Objectives

Successful students:

• Establish fundamental theoretical knowledge in the statistical learning field
• Acquire core knowledge and practical skills in basic techniques of machine learning, including linear/nonlinear methods
• Be competent with theoretical analysis and formulation of statistical learning techniques for solving real-world data mining problems.
• Be familiar with the wide class of supervised/unsupervised data analysis, classification, and regression methods, including linear/logistic regression, kernel methods, neural networks, and other methods.

📚 Course learning outcomes

After this course, students will know the following areas:

• Demonstrate an understanding of different types of learning algorithms used in engineering fields.
• Design and implement machine learning algorithms for feature extraction, classification, and clustering.
• Demonstrate hands-on experience with practical data mining using machine learning algorithms and implement those algorithms in different programming languages.