Postgraduate course
2024/2025
Machine Learning
Type:
Elective course
Delivered by:
School of Data Analysis and Artificial Intelligence
When:
1 year, 1 semester
Open to:
students of one campus
Instructors:
Attila Kertesz-Farkas
Language:
English
Course Syllabus
Abstract
This course gives an introduction to the most popular discriminative and differentiable machine learning methods, which are used in supervised learning.
Learning Objectives
- The student should be able to design and implement a basic machine learning system
Expected Learning Outcomes
- Students know about the basic definitions of machine learning, and the evaluation of their performance.
- Student knows about basic linear and non-linear classifiers, decision trees, genetic algorithms.
- The student is familiar with the application independent, theoretical information distance
- The student becomes familiar with the implementation of deep neural networks. The students gain hands-on experience with implementing deep neural networks in python for real-world applications.
- The student becomes familiar with the implementation of recurrent, sequential deep neural networks. The students also gain hands-on experience with implementation of deep neural networks in python for real-world applications with sequential data, such as neural machine translation.
- The student becomes familiar general differentiable architectures
- The student learns about these basic concepts of machine learning.
Course Contents
- Basic methods
- Introduction to machine learning, Evaluation techniques
- Distance functions
- Deep Neural Networks
- Methods for sequential data
- Neural Turing Machines
- Algorithm independent machine learning
