Zobrazeno 1 - 10
of 769
pro vyhledávání: '"Yanikoglu A"'
Autor:
Aktemur, Ege, Zorlutuna, Ege, Bilgili, Kaan, Bok, Tacettin Emre, Yanikoglu, Berrin, Mutluergil, Suha Orhun
We introduce a new approach in distributed deep learning, utilizing Geoffrey Hinton's Forward-Forward (FF) algorithm to speed up the training of neural networks in distributed computing environments. Unlike traditional methods that rely on forward an
Externí odkaz:
http://arxiv.org/abs/2404.08573
Publikováno v:
Cardiovascular Therapeutics, Vol 2020 (2020)
Background. The white blood cell count to mean platelet volume ratio (WMR) is an indicator of inflammation in patients with atherosclerotic disease. Residual SYNTAX Score (RSS) is an objective measure of degree and complexity of residual stenosis aft
Externí odkaz:
https://doaj.org/article/f5602b552d4b407c8e69e66083c46faf
Autor:
Yavuz, Mehmet Can, Yanikoglu, Berrin
Learning a discriminative semantic space using unlabelled and noisy data remains unaddressed in a multi-label setting. We present a contrastive self-supervised learning method which is robust to data noise, grounded in the domain of variational metho
Externí odkaz:
http://arxiv.org/abs/2312.00824
Autor:
Ebru Erol, Kubra Feyza Erol, Rabia Sare Yanikoglu, Cem Taskin, Cagla Kizilarslan Hancer, Gulacti Topcu
Publikováno v:
ACS Omega, Vol 9, Iss 40, Pp 41890-41903 (2024)
Externí odkaz:
https://doaj.org/article/44c1f7c9c0094f6788a78135914736a8
Autor:
Kizilirmak, Firat, Yanikoglu, Berrin
We present a CNN-BiLSTM system for the problem of offline English handwriting recognition, with extensive evaluations on the public IAM dataset, including the effects of model size, data augmentation and the lexicon. Our best model achieves 3.59\% CE
Externí odkaz:
http://arxiv.org/abs/2307.00664
Autor:
Nowroozi, Ehsan, Mekdad, Yassine, Conti, Mauro, Milani, Simone, Uluagac, Selcuk, Yanikoglu, Berrin
Recently, the popularity and wide use of the last-generation video conferencing technologies created an exponential growth in its market size. Such technology allows participants in different geographic regions to have a virtual face-to-face meeting.
Externí odkaz:
http://arxiv.org/abs/2204.11853
Autor:
Yanikoglu, Reyhan1 (AUTHOR) reyhanyanikoglu@gmail.com, Karakas, Canan Yagmur2 (AUTHOR), Ciftci, Fatih3 (AUTHOR), Insel, Mert Akın4 (AUTHOR), Karavelioglu, Zeynep1,5 (AUTHOR), Varol, Rahmetullah6,7 (AUTHOR), Yilmaz, Abdurrahim6 (AUTHOR), Cakir, Rabia1,8 (AUTHOR), Uvet, Hüseyin6 (AUTHOR), Ustundag, Cem Bulent1,9 (AUTHOR)
Publikováno v:
Pharmaceutics. Jun2024, Vol. 16 Issue 6, p837. 16p.
Publikováno v:
In Energy & Buildings 1 December 2024 324
Autor:
Yanikoglu, Özge1 ozge.peksatici@ozyegin.edu.tr
Publikováno v:
Hacettepe University Journal of Economics & Administrative Sciences / Hacettepe Üniversitesi Iktisadi ve Idari Bilimler Fakültesi Dergisi. haz2024, Vol. 42 Issue 2, p341-362. 22p.
Autor:
Ahmed, Sara Atito Ali, Yavuz, Mehmet Can, Sen, Mehmet Umut, Gulsen, Fatih, Tutar, Onur, Korkmazer, Bora, Samanci, Cesur, Sirolu, Sabri, Hamid, Rauf, Eryurekli, Ali Ergun, Mammadov, Toghrul, Yanikoglu, Berrin
Detecting COVID-19 in computed tomography (CT) or radiography images has been proposed as a supplement to the definitive RT-PCR test. We present a deep learning ensemble for detecting COVID-19 infection, combining slice-based (2D) and volume-based (3
Externí odkaz:
http://arxiv.org/abs/2105.08506