Course title:
Introduction to Machine Learning
Primary programme:
Fizikus mérnök BSc
ECTS credits:
4
Course type:
compulsory
Number of lectures per week:
1
Number of practices per week:
0
Number of laboratory exercises per week:
2
Further knowledge transfer methods:
Grading:
Coursework grade
Special grading methods:
project work, homework
Semester:
4
Prerequisites:
Introduction to Numerical Algorithms
Responsible lecturer:
Dr. János Török, associate professor, PhD
Lecturers and instructors:
Course description:
Basic methods of machine learning and their implementation in python language
Subjects:
Data types, handling, cleaning and normalization
General many parameter fitting
Linear and logistic regression
Parameter importance
Creation of synthetic data
Decision tree
Dimension reduction, relevant measures
Hierarchical clustering
Basics of neural networks: Neurons, activation
Neural networks deep neural networks
Their teaching and application of neural networks
Regularization
Reading materials:
Norvig, P. Russell, and S. Artificial Intelligence. A modern approach. Upper Saddle River, NJ, USA:: Prentice Hall, 2002. ISBN-13: 9780137505135
https://hmkcode.com/ai/backpropagation-step-by-step/
Chollet, Francois. Deep learning with Python. Simon and Schuster, 2021. ISBN-13: 978-1617296864
List of competences:
Please find the detailed list, as quoted from the Hungarian training and outcome requirements of the Physicist Engineer program, in the Hungarian version of the course description.