Graduate study programme

Back   Schedule   Hrvatski

Machine Learning in Systems of Autonomous Networked Vehicles DAEng3-03

ECTS 5 | P 30 | A 0 | L 15 | K 15 | ISVU 177877 | Academic year: 2019./2020.

Course groups

Prikaži sve grupe na predmetu

Course lecturers

VAJAK DENIS, Associate


Introduce students to principles of data analysis and machine learning methods. Enable students to apply machine learning methods in intelligent transport systems of autonomous and networked vehicles, focusing on image processing and deep learning. Acquire appropriate skills for work with development tools for data analysis and machine learning, as well as with development tools that enable the implementation of the developed algorithms to the target platform.

Conditions for enrollment

Requirements met for enrolling in the study programme

Course description

Introduction to machine learning. Unsupervised, supervised learning and reinforcement learning. Parametric and nonparametric methods. Regression and classification methods. Model complexity. Model selection. Results evaluation. Different methods / algorithms of supervised machine learning: linear regression, neural networks, support vector machines, decision trees, random forests. Data clustering, dimensionality reduction and feature extraction. Kalman filter and Bayesian estimation. Anomaly detection. The basics of deep learning. Architectures and deep learning algorithms. Different types of deep neural networks. Convolution Neural Networks. Different applications of machine and deep learning in intelligent transport systems: fusion of sensor inputs, segmentation, detection and classification of objects (signs, lines, pedestrians, etc) in the image, motion planning, learning with and without the driver, local autonomous vehicle control, centralised and distributed control of networked vehicles. Work with development tools that support machine learning and deep learning. Implementation of machine learning algorithms on the target platform.

Student requirements

Defined by the Student evaluation criteria of the Faculty of Electrical Engineering, Computer Science and Information Technology Osijek and paragraph 1.9

Monitoring of students

Defined by the Student evaluation criteria of the Faculty of Electrical Engineering, Computer Science and Information Technology Osijek and paragraph 1.9

Obligatory literature

1. 1 I. Goodfellow, Y. Bengio, A Courville Deep Learning MIT Press, 2016.

2. 2 E. Alpaydin Introduction to Machine Learning MIT Press, 2014.

Pretraži literaturu na:

Recommended additional literature

1. 1 S. Raschka Python Machine Learning Packt Publishing, 2015.

Course assessment

Conducting university questionnaires on teachers (student-teacher relationship, transparency of assessment criteria, motivation for teaching, teaching clarity, etc.). Conducting Faculty surveys on courses (upon passing the exam, student self-assessment of the adopted learning outcomes and student workload in relation to the number of ECTS credits allocated to activities and courses as a whole).

Overview of course assesment

Learning outcomes
Upon successful completion of the course, students will be able to:

1. define basic terminology and the concept of machine learning

2. differentiate machine learning types

3. develop your own software solution using appropriate libraries that contain implemented methods and machine learning algorithms

4. classify, explain and analyse deep neural networks architectures and deep learning algorithms

5. choose and apply appropriate methods and deep learning models to solving specific problems in intelligent transport systems

6. adjust your own software solution based on deep learning methods for implementation on the target platform

Aktivnosti studenta: Vidi tablicu aktivnosti