no code implementations • 16 Feb 2021 • Adil Kaan Akan, Emre Akbas, Fatos T. Yarman Vural
The noise added to the original image is defined as the gradient of the cost function of the model.
no code implementations • 29 Jan 2020 • Adil Kaan Akan, Mehmet Ali Genc, Fatos T. Yarman Vural
We define Just Noticeable Difference for a machine learning model and generate a least perceptible difference for adversarial images which can trick a model.
no code implementations • 7 Dec 2018 • Lubna Shibly Mokatren, Rashid Ansari, Ahmet Enis Cetin, Alex D. Leow, Olusola Ajilore, Heide Klumpp, Fatos T. Yarman Vural
The problem of detecting the presence of Social Anxiety Disorder (SAD) using Electroencephalography (EEG) for classification has seen limited study and is addressed with a new approach that seeks to exploit the knowledge of EEG sensor spatial configuration.
no code implementations • 10 Oct 2018 • Abdullah Alchihabi, Omer Ekmekci, Baran B. Kivilcim, Sharlene D. Newman, Fatos T. Yarman Vural
The network properties of the estimated brain networks are studied in order to identify regions of interest, such as hubs and subgroups of densely connected brain regions.
1 code implementation • 22 Jul 2018 • Baran Baris Kivilcim, Itir Onal Ertugrul, Fatos T. Yarman Vural
We observe that both undirected and directed brain networks surpass the performances of the network models used in the fMRI literature.
no code implementations • 13 Aug 2017 • Arash Rahnama, Abdullah Alchihabi, Vijay Gupta, Panos Antsaklis, Fatos T. Yarman Vural
We suggest a deep architecture which learns the natural groupings of the connectivity patterns of human brain in multiple time-resolutions.
no code implementations • 9 Feb 2017 • Arman Afrasiyabi, Ozan Yildiz, Baris Nasir, Fatos T. Yarman Vural, A. Enis Cetin
This "product" is used to construct a vector product in $R^N$.
no code implementations • 17 Oct 2016 • Itir Onal Ertugrul, Mete Ozay, Fatos T. Yarman Vural
In this work, we propose a novel framework to encode the local connectivity patterns of brain, using Fisher Vectors (FV), Vector of Locally Aggregated Descriptors (VLAD) and Bag-of-Words (BoW) methods.
no code implementations • EMNLP 2016 • Orhan Firat, Baskaran Sankaran, Yaser Al-Onaizan, Fatos T. Yarman Vural, Kyunghyun Cho
In this paper, we propose a novel finetuning algorithm for the recently introduced multi-way, mulitlingual neural machine translate that enables zero-resource machine translation.
no code implementations • 3 Mar 2016 • Itir Onal, Mete Ozay, Eda Mizrak, Ilke Oztekin, Fatos T. Yarman Vural
The corresponding cognitive process, encoded in the brain, is then represented by these meshes each of which is estimated assuming a linear relationship among the voxel time series in a predefined locality.
no code implementations • 22 Mar 2015 • Mete Ozay, Inaki Esnaola, Fatos T. Yarman Vural, Sanjeev R. Kulkarni, H. Vincent Poor
The relationships between statistical and geometric properties of attack vectors employed in the attack scenarios and learning algorithms are analyzed to detect unobservable attacks using statistical learning methods.
no code implementations • 18 Feb 2015 • Mete Ozay, Fatos T. Yarman Vural, Sanjeev R. Kulkarni, H. Vincent Poor
A new segmentation fusion method is proposed that ensembles the output of several segmentation algorithms applied on a remotely sensed image.
no code implementations • 23 Dec 2014 • Orhan Firat, Emre Aksan, Ilke Oztekin, Fatos T. Yarman Vural
By employing the proposed temporal convolutional architecture with spatial pooling, raw input fMRI data is mapped to a non-linear, highly-expressive and low-dimensional feature space where the final classification is conducted.
no code implementations • 23 Feb 2014 • Orhan Firat, Mete Ozay, Ilke Oztekin, Fatos T. Yarman Vural
The proposed method was tested on a recognition memory experiment, including data pertaining to encoding and retrieval of words belonging to ten different semantic categories.
no code implementations • 10 May 2012 • Mete Ozay, Ilke Öztekin, Uygar Öztekin, Fatos T. Yarman Vural
The arc weights of each mesh are estimated from the voxel intensity values by least squares method.
1 code implementation • 1 Apr 2012 • Mete Ozay, Fatos T. Yarman Vural
In this study, a new Stacked Generalization technique called Fuzzy Stacked Generalization (FSG) is proposed to minimize the difference between N -sample and large-sample classification error of the Nearest Neighbor classifier.