Browsing Faculty of Engineering by Author "(ORCID 0000-0001-6293-3656 & YÖK ID 258737) Kandemir, Melih"
Now showing items 1-7 of 7
-
On context-aware DDoS attacks using deep generative networks
Gürsun, Gonca; Şensoy, Murat; Kandemir, Melih (IEEE, 2018-10)Distributed Denial of Service (DDoS) attacks continue to be one of the most severe threats in the Internet. The intrinsic challenge in preventing DDoS attacks is to distinguish them from legitimate flash crowds since two ... -
Prediction of active UE number with Bayesian neural networks for self-organizing LTE networks
Narmanlıoğlu, Ö.; Zeydan, E.; Kandemir, Melih; Kranda, T. (IEEE, 2017-01-01)Internet-empowered electronic gadgets and content rich multimedia applications have expanded exponentially in recent years. As a consequence, heterogeneous network structures introduced with Long Term Evolution (LTE) ... -
Sampling-free variational inference of bayesian neural networks by variance backpropagation
Haußmann, M.; Hamprecht, F. A.; Kandemir, Melih (ML Research Press, 2020)We propose a new Bayesian Neural Net formulation that affords variational inference for which the evidence lower bound is analytically tractable subject to a tight approximation. We achieve this tractability by (i) decomposing ... -
Sampling-free variational inference of Bayesian neural networks by variance backpropagation
Haußmann, M.; Hamprecht, F. A.; Kandemir, Melih (Association For Uncertainty in Artificial Intelligence (AUAI), 2019)We propose a new Bayesian Neural Net formulation that affords variational inference for which the evidence lower bound is analytically tractable subject to a tight approximation. We achieve this tractability by (i) decomposing ... -
Supervising topic models with Gaussian processes
Kandemir, Melih; Kekeç, T.; Yeniterzi, Reyyan (Elsevier, 2018-05)Topic modeling is a powerful approach for modeling data represented as high-dimensional histograms. While the high dimensionality of such input data is extremely beneficial in unsupervised applications including language ... -
Variational bayesian multiple instance learning with gaussian processes
Haussmann, M.; Hamprecht, F. A.; Kandemir, Melih (IEEE, 2017)Gaussian Processes (GPs) are effective Bayesian predictors. We here show for the first time that instance labels of a GP classifier can be inferred in the multiple instance learning (MIL) setting using variational Bayes. ... -
Variational closed-Form deep neural net inference
Kandemir, Melih (Elsevier, 2018-09)We introduce a Bayesian construction for deep neural networks that is amenable to mean field variational inference that operates solely by closed-form update rules. Hence, it does not require any learning rate to be manually ...
Share this page