Zobrazeno 1 - 10
of 192
pro vyhledávání: '"ULUSOY, İlkay"'
Publikováno v:
IOP Neuromorphic Computing and Engineering 2024 4 (1)
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:
http://arxiv.org/abs/2303.12167
Few-shot segmentation aims to devise a generalizing model that segments query images from unseen classes during training with the guidance of a few support images whose class tally with the class of the query. There exist two domain-specific problems
Externí odkaz:
http://arxiv.org/abs/2211.02300
In this paper, an LSTM autoencoder-based architecture is utilized for drowsiness detection with ResNet-34 as feature extractor. The problem is considered as anomaly detection for a single subject; therefore, only the normal driving representations ar
Externí odkaz:
http://arxiv.org/abs/2209.05269
Autor:
Ulusoy, Ilkay, Geduk, Salih
Publikováno v:
In Journal of Neuroscience Methods September 2024 409
Autor:
Algan, Görkem, Ulusoy, Ilkay
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:
http://arxiv.org/abs/2103.10869
Computer vision systems recently made a big leap thanks to deep neural networks. However, these systems require correctly labeled large datasets in order to be trained properly, which is very difficult to obtain for medical applications. Two main rea
Externí odkaz:
http://arxiv.org/abs/2010.06939
Autor:
Algan, Görkem, Ulusoy, Ilkay
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:
http://arxiv.org/abs/2007.05836
Autor:
Algan, Görkem, Ulusoy, İlkay
The recent success of deep learning is mostly due to the availability of big datasets with clean annotations. However, gathering a cleanly annotated dataset is not always feasible due to practical challenges. As a result, label noise is a common prob
Externí odkaz:
http://arxiv.org/abs/2003.10471
Autor:
Algan, Görkem, Ulusoy, Ilkay
Image classification systems recently made a giant leap with the advancement of deep neural networks. However, these systems require an excessive amount of labeled data to be adequately trained. Gathering a correctly annotated dataset is not always f
Externí odkaz:
http://arxiv.org/abs/1912.05170