Course Description

  • Supervised learning, Neural networks, Support vector machines, Decision tree, Random forest, k-nearest neighbors.
  • Introduction to ensemble and deep learning.
  • Introduction to TinyML.
  • Application of approximate calculations.
  • Machine learning application development tools and software.
  • Implementation of systems (at hardware and software level) with machine learning techniques.

Course Details

Code:  ΗΤΕ 403

Type:  General Elective

Semester: 

Hours per week:   3

ECTS units:  5

Instructors:  S. Goudos, K. Siozios