témavezető: Hajdu András
helyszín (magyar oldal): University of Debrecen, Faculty of Informatics helyszín rövidítés: ITDI
A kutatási téma leírása:
The aim of the research is to design and optimize machine learning procedures for dedicated tasks. The topic is motivated by the fact that though numerous universal efficient classic and deep learning techniques have been proposed in the recent years, they are not always optimal for specific application scenarios, so further optimization and change in their designs are necessary. One typical example is the convolutional neural networks, where the popular architectures are trained in natural image databases, however, in the given application the important patterns and features are simpler or more complex for successful classification, detection or segmentation purposes. So the goal is to design such architectures that fits better to the given challenge regarding e.g. the semantical rules characterizing the specific situation. Possible application fields: molecular analysis and design, image classification/segmentation mainly for clinical applications, text analysis with natural language processing tools.
Bibliography
1. Yoshua Bengio, Ian J. Goodfellow, Aaron Courville: Deep Learning, MIT Press, 2015.
2. Tariq Rashid: Make Your Own Neural Network (1st ed.). CreateSpace Independent Publishing Platform, USA, 2016.
3. Terrence J. Sejnowski: The Deep Learning Revolution, The MIT Press, 2018.
4. Suvrit Sra, Sebastian Nowozin, and Stephen J. Wright: Optimization for Machine Learning, The MIT Press, 2011.
Jelentkezési határidő: 2024-05-15
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).
Bejelentkezés
