1 code implementation • 14 Mar 2023 • Uğurcan Çakal, Maryada, Chenxi Wu, Ilkay Ulusoy, Dylan R. Muir
Here we demonstrate a novel methodology for ofDine training and deployment of spiking neural networks (SNNs) to the mixed-signal neuromorphic processor DYNAP-SE2.
no code implementations • 19 Mar 2021 • Görkem Algan, Ilkay Ulusoy
In order to address this problem, we propose a label noise robust learning algorithm, in which the base classifier is trained on soft-labels that are produced according to a meta-objective.
no code implementations • 14 Oct 2020 • Görkem Algan, Ilkay Ulusoy, Şaban Gönül, Banu Turgut, Berker Bakbak
Moreover, medical imaging datasets are commonly tiny, which makes each data very important in learning.
1 code implementation • 11 Jul 2020 • Görkem Algan, Ilkay Ulusoy
In order to iteratively update soft labels, meta-gradient descent step is performed on estimated labels, which would minimize the loss of noise-free meta samples.
1 code implementation • 11 Dec 2019 • Görkem Algan, Ilkay Ulusoy
Because of these practical challenges, label noise is a common problem in real-world datasets, and numerous methods to train deep neural networks with label noise are proposed in the literature.