Výsledky vyhledávání - "TURAN, Çiğdem"

Report

Gender Bias in BERT -- Measuring and Analysing Biases through Sentiment Rating in a Realistic Downstream Classification Task

Autor: Jentzsch, Sophie, Turan, Cigdem

Publikováno v: Proceedings of the 4th Workshop on Gender Bias in Natural Language Processing (GeBNLP) (2022); Pages 184-199

Pretrained language models are publicly available and constantly finetuned for various real-life applications. As they become capable of grasping complex contextual information, harmful biases are likely increasingly intertwined with those models. Th

Externí odkaz: http://arxiv.org/abs/2306.15298

Zobrazit plný text záznamu

Report

Large Pre-trained Language Models Contain Human-like Biases of What is Right and Wrong to Do

Autor: Schramowski, Patrick, Turan, Cigdem, Andersen, Nico, Rothkopf, Constantin A., Kersting, Kristian

Artificial writing is permeating our lives due to recent advances in large-scale, transformer-based language models (LMs) such as BERT, its variants, GPT-2/3, and others. Using them as pre-trained models and fine-tuning them for specific tasks, resea

Externí odkaz: http://arxiv.org/abs/2103.11790

Zobrazit plný text záznamu

Report

Alfie: An Interactive Robot with a Moral Compass

Autor: Turan, Cigdem, Schramowski, Patrick, Rothkopf, Constantin, Kersting, Kristian

This work introduces Alfie, an interactive robot that is capable of answering moral (deontological) questions of a user. The interaction of Alfie is designed in a way in which the user can offer an alternative answer when the user disagrees with the

Externí odkaz: http://arxiv.org/abs/2009.05349

Zobrazit plný text záznamu

Report

BERT has a Moral Compass: Improvements of ethical and moral values of machines

Autor: Schramowski, Patrick, Turan, Cigdem, Jentzsch, Sophie, Rothkopf, Constantin, Kersting, Kristian

Allowing machines to choose whether to kill humans would be devastating for world peace and security. But how do we equip machines with the ability to learn ethical or even moral choices? Jentzsch et al.(2019) showed that applying machine learning to

Externí odkaz: http://arxiv.org/abs/1912.05238

Zobrazit plný text záznamu

Report

Soft Locality Preserving Map (SLPM) for Facial Expression Recognition

Autor: Turan, Cigdem, Lam, Kin-Man, He, Xiangjian

For image recognition, an extensive number of methods have been proposed to overcome the high-dimensionality problem of feature vectors being used. These methods vary from unsupervised to supervised, and from statistics to graph-theory based. In this

Externí odkaz: http://arxiv.org/abs/1801.03754

Zobrazit plný text záznamu

Akademický článek

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Akademický článek

Histogram-based local descriptors for facial expression recognition (FER): A comprehensive study

Autor: Turan, Cigdem, Lam, Kin-Man

Publikováno v: In Journal of Visual Communication and Image Representation August 2018 55:331-341

Zobrazit plný text záznamu

Hypersurfaces Families with Common Non-Null Isoasymptotic Curve in Lorentz Minkowski 4-Space

Autor: TURAN, Çiğdem, ALTIN, Mustafa, KARADAĞ, Hacı Bayram

Publikováno v: Issue: 38 99-109
European Journal of Science and Technology
Avrupa Bilim ve Teknoloji Dergisi

In this study, the parametric equation of hypersurfaces passing through the spacelike and timelike curves that has non-null Frenet vectors in E_1^4 Lorentz Minkowski space was expressed with the help of this curve is Frenet frame. Furthermore, hypers

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::af031caba9c63bb2c0611cfc35d52431
https://doi.org/10.31590/ejosat.1093177

Zobrazit plný text záznamu

Akademický článek

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Akademický článek

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Vyhledávací nástroje:

Upřesnit hledání