Výsledky vyhledávání - "Utku Ozbulak"

Akademický článek

Assessing the reliability of point mutation as data augmentation for deep learning with genomic data

Autor: Hyunjung Lee, Utku Ozbulak, Homin Park, Stephen Depuydt, Wesley De Neve, Joris Vankerschaver

Publikováno v: BMC Bioinformatics, Vol 25, Iss 1, Pp 1-19 (2024)

Abstract Background Deep neural networks (DNNs) have the potential to revolutionize our understanding and treatment of genetic diseases. An inherent limitation of deep neural networks, however, is their high demand for data during training. To overco

Externí odkaz: https://doaj.org/article/979cd6ed040146ed80923cd0aca97af4

Zobrazit plný text záznamu

Plný text ve formátu HTML

Akademický článek

Tryp: a dataset of microscopy images of unstained thick blood smears for trypanosome detection

Autor: Esla Timothy Anzaku, Mohammed Aliy Mohammed, Utku Ozbulak, Jongbum Won, Hyesoo Hong, Janarthanan Krishnamoorthy, Sofie Van Hoecke, Stefan Magez, Arnout Van Messem, Wesley De Neve

Publikováno v: Scientific Data, Vol 10, Iss 1, Pp 1-12 (2023)

Abstract Trypanosomiasis, a neglected tropical disease (NTD), challenges communities in sub-Saharan Africa and Latin America. The World Health Organization underscores the need for practical, field-adaptable diagnostics and rapid screening tools to a

Externí odkaz: https://doaj.org/article/b624826857cb45d29b9f63dc1d90e105

Zobrazit plný text záznamu

Mutate and observe: utilizing deep neural networks to investigate the impact of mutations on translation initiation

Autor: Utku Ozbulak, Hyun Jung Lee, Jasper Zuallaert, Wesley De Neve, Stephen Depuydt, Joris Vankerschaver

Publikováno v: BIOINFORMATICS

Motivation The primary regulatory step for protein synthesis is translation initiation, which makes it one of the fundamental steps in the central dogma of molecular biology. In recent years, a number of approaches relying on deep neural networks (DN

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f8e0dad95fabd2a4e91d507f008a750e
https://biblio.ugent.be/publication/01H66699YYAHCG4VH7WHSPK3BY/file/01H6669VM6KEFSDP4ERAP63Y17

Zobrazit plný text záznamu

Perturbation analysis of gradient-based adversarial attacks

Autor: Arnout Van Messem, Wesley De Neve, Manvel Gasparyan, Utku Ozbulak

Publikováno v: Pattern Recognition Letters. 135:313-320

After the discovery of adversarial examples and their adverse effects on deep learning models, many studies focused on finding more diverse methods to generate these carefully crafted samples. Although empirical results on the effectiveness of advers

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::064cd293082460be9f1d728d0d0acfde
https://doi.org/10.1016/j.patrec.2020.04.034

Zobrazit plný text záznamu

Investigating the significance of adversarial attacks and their relation to interpretability for radar-based human activity recognition systems

Autor: Azarakhsh Jalalvand, Utku Ozbulak, Wesley De Neve, Arnout Van Messem, Baptist Vandersmissen, Ivo Couckuyt

Publikováno v: COMPUTER VISION AND IMAGE UNDERSTANDING

Given their substantial success in addressing a wide range of computer vision challenges, Convolutional Neural Networks (CNNs) are increasingly being used in smart home applications, with many of these applications relying on the automatic recognitio

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::aa68ee962af0abc9d0f83042a82a9896

Zobrazit plný text záznamu

Automatic Detection of Trypanosomosis in Thick Blood Smears Using Image Pre-processing and Deep Learning

Autor: Taewoo Jung, Utku Ozbulak, Stefan Magez, Arnout Van Messem, Esla Timothy Anzaku, Wesley De Neve

Publikováno v: Intelligent Human Computer Interaction ISBN: 9783030684518
IHCI (2)

Trypanosomosis, which is caused by the Trypanosoma parasite, is an infectious disease that affects both humans and animals. Today, the microscopic examination of a Giemsa or Wright stained blood smear from an infected individual is the standard proce

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::f9189076bd3d37c2cb0b8a3189c89c40
https://doi.org/10.1007/978-3-030-68452-5_27

Zobrazit plný text záznamu

Not All Adversarial Examples Require a Complex Defense: Identifying Over-optimized Adversarial Examples with IQR-based Logit Thresholding

Autor: Wesley De Neve, Utku Ozbulak, Arnout Van Messem

Publikováno v: IJCNN
2019 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN)

Detecting adversarial examples currently stands as one of the biggest challenges in the field of deep learning. Adversarial attacks, which produce adversarial examples, increase the prediction likelihood of a target class for a particular data point.

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6c8596bc31a872f042fd5d962b831b54
https://doi.org/10.1109/ijcnn.2019.8851930

Zobrazit plný text záznamu

Impact of adversarial examples on deep learning models for biomedical image segmentation

Autor: Wesley De Neve, Utku Ozbulak, Arnout Van Messem

Publikováno v: MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION-MICCAI 2019, PT II
Lecture Notes in Computer Science ISBN: 9783030322441
MICCAI (2)

Deep learning models, which are increasingly being used in the field of medical image analysis, come with a major security risk, namely, their vulnerability to adversarial examples. Adversarial examples are carefully crafted samples that force machin

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fb8069464ea11923576bf8f34ee2b3b1
https://biblio.ugent.be/publication/8632073/file/8632075

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání