Thesis supervisor: Balázs Harangi
Location of studies (in Hungarian): University of Debrecen Faculty of Informatics Abbreviation of location of studies: DE IK
Description of the research topic:
Syllabus
The aim of this research is the adaptation and developing of the state-of-the-art classifier algorithms which applies the latest research results from the field of machine learning. The developed application mainly connects to medical problem and the data comes from different imaging modalities like RGB image, CT, PET and ultrasonic tools. During the work, many conventional image processing techniques and image pre-processing methods will be used but the deep convolutional neural networks and their ensembles will be enhanced also. The training dataset and its extension will be a very important question and the appropriate solutions should be found.
Bibliography
1. Yoshua Bengio, Ian J. Goodfellow, Aaron Courville: Deep Learning, MIT Press, 2015.
2. B. Cyganek: Object Detection and Recognition in Digital Images: Theory and Practice, John Wiley & Sons Ltd., New York, 2013.
3. Terrence J. Sejnowski: The Deep Learning Revolution, The MIT Press, 2018.
4. Ian H. Witten, Eibe Frank, Mark A. Hall, and Christopher J. Pal. Data Mining: Practical Machine Learning Tools and Techniques. Morgan Kaufmann, Burlington, MA, 4 edition, 2016.
Deadline for application: 2019-11-15
2024. IV. 17. ODT ülés Az ODT következő ülésére 2024. június 14-én, pénteken 10.00 órakor kerül sor a Semmelweis Egyetem Szenátusi termében (Bp. Üllői út 26. I. emelet).
Login
