no code implementations • 13 Dec 2021 • Dan Kluser, Jonas Bokstaller, Samuel Rutz, Tobias Buner
The restriction to the l2-distance metric allows for the use of blocked distance evaluations which significantly increase performance for high dimensional datasets.
no code implementations • 29 Sep 2021 • Jonas Bokstaller, Yihang She, Zhehan Fu, Tommaso Macrì
The image classification problem has been deeply investigated by the research community, with computer vision algorithms and with the help of Neural Networks.
no code implementations • 20 Sep 2021 • Jonas Bokstaller, Costanza Maria Improta
The Human-Machine Interaction (HMI) research field is an important topic in machine learning that has been deeply investigated thanks to the rise of computing power in the last years.
no code implementations • 20 Sep 2021 • Aygul Zagidullina, Georgios Patoulidis, Jonas Bokstaller
In this paper, a BERT based neural network model is applied to the JIGSAW data set in order to create a model identifying hateful and toxic comments (strictly seperated from offensive language) in online social platforms (English language), in this case Twitter.