Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Blaz Skrlj"'
Autor:
Ruben Perellón-Alfonso, Aleš Oblak, Matija Kuclar, Blaž Škrlj, Indre Pileckyte, Borut Škodlar, Peter Pregelj, Kilian Abellaneda-Pérez, David Bartrés-Faz, Grega Repovš, Jurij Bon
Publikováno v:
Frontiers in Psychiatry, Vol 14 (2023)
IntroductionPatients with schizophrenia typically exhibit deficits in working memory (WM) associated with abnormalities in brain activity. Alterations in the encoding, maintenance and retrieval phases of sequential WM tasks are well established. Howe
Externí odkaz:
https://doaj.org/article/51794d2c07d043419e5a367b9a85ddbc
Publikováno v:
Machine Learning and Knowledge Extraction, Vol 4, Iss 4, Pp 1107-1123 (2022)
Increasing quantities of semantic resources offer a wealth of human knowledge, but their growth also increases the probability of wrong knowledge base entries. The development of approaches that identify potentially spurious parts of a given knowledg
Externí odkaz:
https://doaj.org/article/03722ffab5a24d4582e367c232ffe6b9
Publikováno v:
Machine Learning and Knowledge Extraction, Vol 5, Iss 1, Pp 1-13 (2022)
With the increasing amounts of available data, learning simultaneously from different types of inputs is becoming necessary to obtain robust and well-performing models. With the advent of representation learning in recent years, lower-dimensional vec
Externí odkaz:
https://doaj.org/article/6b8718ffe6cc481b8bc9653da310d48e
Autor:
Blaž Škrlj, Benjamin Renoust
Publikováno v:
Applied Network Science, Vol 5, Iss 1, Pp 1-34 (2020)
Abstract Complex networks, such as transportation networks, social networks, or biological networks, capture the complex system they model by often representing only one type of interactions. In real world systems, there may be many different aspects
Externí odkaz:
https://doaj.org/article/6cab386186cd4c3b80df0dfe9054bd5c
Publikováno v:
Applied Network Science, Vol 4, Iss 1, Pp 1-24 (2019)
Abstract Complex networks are used as means for representing multimodal, real-life systems. With increasing amounts of data that lead to large multilayer networks consisting of different node and edge types, that can also be subject to temporal chang
Externí odkaz:
https://doaj.org/article/7b0b39318a194e439e30d969f11374ac
Autor:
Samo Lešnik, Blaž Škrlj, Nika Eržen, Urban Bren, Stanislav Gobec, Janez Konc, Dušanka Janežič
Publikováno v:
Journal of Cheminformatics, Vol 9, Iss 1, Pp 1-8 (2017)
Abstract We describe a novel freely available web server Base of Bioisosterically Exchangeable Replacements (BoBER), which implements an interface to a database of bioisosteric and scaffold hopping replacements. Bioisosterism and scaffold hopping are
Externí odkaz:
https://doaj.org/article/37ac38fc940c45648545cf1badf8de04
Publikováno v:
Applied Sciences, Vol 10, Iss 17, p 5993 (2020)
In this paper, we address the task of zero-shot cross-lingual news sentiment classification. Given the annotated dataset of positive, neutral, and negative news in Slovene, the aim is to develop a news classification system that assigns the sentiment
Externí odkaz:
https://doaj.org/article/f4a65ef29e0c412c9bcdd75a81419a18
Publikováno v:
IEEE Access, Vol 8, Pp 212568-212588 (2020)
Learning from complex real-life networks is a lively research area, with recent advances in learning information-rich, low-dimensional network node representations. However, state-of-the-art methods are not necessarily interpretable and are therefore
Externí odkaz:
https://doaj.org/article/c910ba24914344c1bec96dbd31373d6a
Autor:
Marina Dermastia, Blaz Skrlj, Anita Valmarska, Rebeka Strah, Novak Marusa Pompe, Barbara Anzic, Spela Tomaz, Maja Kriznik, Christina Schonhuber, Monika Riedle-Bauer, Marko Petek, Ales Kladnik, Nada Lavrac, Kristina Gruden, Thomas Roitsch, Gunter Brader
Publikováno v:
Phytopathogenic Mollicutes. 13:9-10
Autor:
Blaz Skrlj, Matej Petkovic
Contemporary natural language processing (NLP) revolves around learning from latent document representations, generated either implicitly by neural language models or explicitly by methods such as doc2vec or similar. One of the key properties of the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c788829eae2e6799448009099ba1c893