Research Areas ǀ Machine Learning

Icons-01

In the area of Maschine Learning, we are focusing on multi-target prediction and representation learning.

In the field of multi-target prediction, we are developing various methods addressing different machine learning tasks. (1) We are designing novel methods for learning oblique decision trees for simple supervised tasks such as classification and regression, as well as for more complex supervised tasks from structured output prediction such as multi-label classification, hierarchical multi-label classification, and multi-target regression. (2) We are extending these methods towards semi-supervised learning for both simple and complex learning tasks (such as structured output prediction). (3) We are developing a methodology for fusing different evaluation measures in the context of recommender systems. (4) We are performing a study to analyze and explain the performance of multi-label classification methods with data set properties.

We are also addressing the topic of representation learning, where we are developing data mining methods for the analysis of heterogeneous data, and using them in several application domains.

 

Projects in the field of Machine Learning:

INQUIRE

Identification of chemical and biological determinants, their sources, and strategies to promote healthier homes in Europe, 01.09.2022 - 31.8.2027, Sašo Džeroski

N2-0236

Intelligent inference system for biological discoveries and its application to cancer research, 01.01.2022 - 31.12.2024, Sašo Džeroski

DIH4AI-Senso4S

DIH4AI-Senso4S-E8, 01.01.2022-30.04.2022, Benrnard Ženko, Martin Žnidaršič

PARC

Partnership for the Assessment of Risks from Chemicals, 01.05.2022 - 30.04.2029, Sašo Džeroski, Panče Panov

P2-0103

Knowledge technologies, 1.1.2022 - 31.12.2027, Sašo Džeroski

J3-3070

Determining the origin of liver metastases from liquid biopsy, 1.10.2021-30.9.2024, Sašo Džeroski

J4-3095

Application of single cell sequencing and machine learning in mammary gland biology, 1.10.2021-30.9.2024, Sašo Džeroski

J1-3033

Innovative isotopic techniques for identification of sources and biogeochemical cycling of mercury in contaminated sites - IsoCont, 1.10.2021-30.9.2024, Sašo Džeroski

J4-2544

CRISPR/CAS9-mediated targeted mutagenesis for resistance of grapevine and potato against phytoplasmas, 1.11.2020-31.10.2023, Nada Lavrač

V3-2033

Clinical course and outcome of Covid-19, 1.10.2020-30.9.2022, Sašo Džeroski, Nada Lavrač