Thesis topic proposal
Richárd Farkas
Machine Learning methods for joint analysis of various modalities


Institute: University of Szeged
computer sciences
PhD School in Computer Science

Thesis supervisor: Richárd Farkas
Location of studies (in Hungarian): SZTE
Abbreviation of location of studies: SZTE

Description of the research topic:

Data science and machine learning has been emerging recently. Separated
solutions and research communities has been developed for the analysis
of various modalities, e.g. numerical databases, networks, time series,
textual content, image/video. On the other hand, there are usually
multiple modalities available in real world tasks. For instance, a robot
have to make decisions based on image, voice and various sensor data and
the analysis of Twitter can utilize the textual content of tweets, the
network of the user, the location of the user.

The chief objective of the doctoral topic is to develop and investigate
novel machine learning algorithms which is able to jointly learn from
various modalities by exploiting synergies and it can outperform the
standard approach of analyzing modalities independently from each other.

Required language skills: english
Number of students who can be accepted: 2

Deadline for application: 2019-03-15

2019. I. 10.
ODT ülés
Az ODT következő ülésére 2019. február 22-én 10.00 órakor kerül sor a Semmelweis Egyetem Szenátusi termében (Bp. Üllői út 26. I. emelet).

All rights reserved © 2007, Hungarian Doctoral Council. Doctoral Council registration number at commissioner for data protection: 02003/0001. Program version: 2.2358 ( 2017. X. 31. )