Zobrazeno 1 - 10
of 97
pro vyhledávání: '"İlkay Ulusoy"'
Publikováno v:
Neuromorphic Computing and Engineering, Vol 4, Iss 1, p 014011 (2024)
Mixed-signal neuromorphic processors provide extremely low-power operation for edge inference workloads, taking advantage of sparse asynchronous computation within spiking neural networks (SNNs). However, deploying robust applications to these device
Externí odkaz:
https://doaj.org/article/c19bedbbb9af41258090422a0d11c475
Autor:
Mehmet Altan Toksöz, İlkay Ulusoy
Publikováno v:
IET Computer Vision, Vol 10, Iss 5, Pp 433-442 (2016)
The authors present a sparsity‐based algorithm, basic thresholding classifier (BTC), for classification applications which is capable of identifying test samples extremely rapidly and performing high classification accuracy. They introduce a suffic
Externí odkaz:
https://doaj.org/article/d96a14e05d3d49d8a853a2c45110270c
Autor:
Nermin, Tepe, Hürrem Evren, Boran, Salih, Gedük, Ergin, Dileköz, İlkay, Ulusoy, Hayrunnisa, Bolay
Publikováno v:
Turkish Journal of Medical Sciences. 52:1371-1377
Discrimination of consecutive sensory stimuli is imperative for proper sensory perception and behavioral response. We aimed to investigate the emergence of paired somatosensory responses in relation to the interstimulus interval (ISI) change.Paired s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7271189f3991b3a5d2e11ddfb7de647c
https://doi.org/10.55730/1300-0144.5444
https://doi.org/10.55730/1300-0144.5444
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031250743
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3071a3a7d11d638a09bd004299f0f577
https://doi.org/10.1007/978-3-031-25075-0_37
https://doi.org/10.1007/978-3-031-25075-0_37
Autor:
Salih Geduk, Ilkay Ulusoy
Publikováno v:
Optimization. 71:2935-2962
Discrete Dynamic Bayesian Network (dDBN) is used in many challenging causal modelling applications, such as human brain connectivity, due to its multivariate, non-deterministic, and nonlinear capab...
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::39d49ba23319e4bdfe2fd613e0b11746
https://doi.org/10.1080/02331934.2021.1892105
https://doi.org/10.1080/02331934.2021.1892105
Publikováno v:
2022 30th Signal Processing and Communications Applications Conference (SIU).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a59f27badfc6229c8c4d37ecb32c3305
https://doi.org/10.1109/siu55565.2022.9864790
https://doi.org/10.1109/siu55565.2022.9864790
Autor:
Ilkay Ulusoy, Botan Yildirim
Publikováno v:
2022 30th Signal Processing and Communications Applications Conference (SIU).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::74a38bc639cbf02fdf5e34c010778bbe
https://doi.org/10.1109/siu55565.2022.9864858
https://doi.org/10.1109/siu55565.2022.9864858
Autor:
Gorkem Algan, Ilkay Ulusoy
Real-world datasets commonly have noisy labels, which negatively affects the performance of deep neural networks (DNNs). In order to address this problem, we propose a label noise robust learning algorithm, in which the base classifier is trained on
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7e169b3ada8ffc47073d056d97737e02
http://arxiv.org/abs/2103.10869
http://arxiv.org/abs/2103.10869
Autor:
Zeynep Kaya, Hulya Karatas, Turgay Dalkara, Buket Dönmez-Demir, Sefik Evren Erdener, Ilkay Ulusoy
Publikováno v:
Scientific Reports
Scientific Reports, Vol 10, Iss 1, Pp 1-10 (2020)
Scientific Reports, Vol 10, Iss 1, Pp 1-10 (2020)
Although cortical spreading depolarizations (CSD) were originally assumed to be homogeneously and concentrically propagating waves, evidence obtained first in gyrencephalic brains and later in lissencephalic brains suggested a rather non-uniform prop
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6dadd99ed1e13151b2f18f833cd582fe
https://pubmed.ncbi.nlm.nih.gov/32732932
https://pubmed.ncbi.nlm.nih.gov/32732932
Autor:
Görkem Algan, Ilkay Ulusoy
Publikováno v:
ICPR
The existence of noisy labels in the dataset causes significant performance degradation for deep neural networks (DNNs). To address this problem, we propose a Meta Soft Label Generation algorithm called MSLG, which can jointly generate soft labels us
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f667df40d71517fce46665466339344d