Zobrazeno 1 - 10
of 222
pro vyhledávání: '"Michael Granitzer"'
Publikováno v:
Frontiers in Education, Vol 8 (2023)
This study reports the Intraclass Correlation Coefficients of feedback ratings produced by OpenAI's GPT-4, a large language model (LLM), across various iterations, time frames, and stylistic variations. The model was used to rate responses to tasks r
Externí odkaz:
https://doaj.org/article/ba4722a5f7fe44e4b02c05698103f5af
Publikováno v:
Frontiers in Artificial Intelligence, Vol 6 (2023)
Generative pre-trained transformers (GPT) have recently demonstrated excellent performance in various natural language tasks. The development of ChatGPT and the recently released GPT-4 model has shown competence in solving complex and higher-order re
Externí odkaz:
https://doaj.org/article/45bb59858be147809444fa83972840bf
Autor:
Clemens Havas, Lorenz Wendlinger, Julian Stier, Sahib Julka, Veronika Krieger, Cornelia Ferner, Andreas Petutschnig, Michael Granitzer, Stefan Wegenkittl, Bernd Resch
Publikováno v:
ISPRS International Journal of Geo-Information, Vol 10, Iss 8, p 498 (2021)
In 2015, within the timespan of only a few months, more than a million people made their way from Turkey to Central Europe in the wake of the Syrian civil war. At the time, public authorities and relief organisations struggled with the admission, tra
Externí odkaz:
https://doaj.org/article/7958668df5b84fdfb54946761c6f86b8
Publikováno v:
Future Internet, Vol 2, Iss 3, Pp 238-258 (2010)
Semantic technologies are of paramount importance to the future Internet. The reuse and integration of semantically described resources, such as data or services, necessitates the bringing of ontologies into mutual agreement. Ontology alignment deals
Externí odkaz:
https://doaj.org/article/d96f6ff40d5d4f1d871047242bf28ad1
Autor:
Fatemeh Salehi Rizi, Michael Granitzer
Publikováno v:
Algorithms, Vol 10, Iss 4, p 109 (2017)
Embedding social network data into a low-dimensional vector space has shown promising performance for many real-world applications, such as node classification, node clustering, link prediction and network visualization. However, the information cont
Externí odkaz:
https://doaj.org/article/b2275545da6440c58e6cc871ce21c3df
Publikováno v:
Knowledge and Information Systems. 64:831-858
The state-of-the-art feature-engineering method for fraud classification of electronic payments uses manually engineered feature aggregates, i.e., descriptive statistics of the transaction history. However, this approach has limitations, primarily th
Publikováno v:
Machine Learning, Optimization, and Data Science ISBN: 9783031258909
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::590796fc27f61d5539d62e23278711de
https://doi.org/10.1007/978-3-031-25891-6_1
https://doi.org/10.1007/978-3-031-25891-6_1
Publikováno v:
Machine Learning and Knowledge Discovery in Databases ISBN: 9783031264115
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c17a099496ed63f0903d080702ec904d
https://doi.org/10.1007/978-3-031-26412-2_28
https://doi.org/10.1007/978-3-031-26412-2_28
Publikováno v:
Proceedings of the 15th International Conference on Agents and Artificial Intelligence.
The use of BERT, one of the most popular language models, has led to improvements in many Natural Language Processing (NLP) tasks. One such task is Named Entity Recognition (NER) i.e. automatic identification of named entities such as location, perso
Publikováno v:
Machine Learning, Optimization, and Data Science ISBN: 9783031255984
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9f99eeb28e36d613bacaf4244cc213f4
https://doi.org/10.1007/978-3-031-25599-1_28
https://doi.org/10.1007/978-3-031-25599-1_28