Yigit Alparslan

Yigit Alparslan

Auto-generated profile, based on publicly available information

Yigit Alparslan

College of Computing & Informatics, Drexel University, PA

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 July 2021
Verified
Conference Paper
Open access
YAYigit Alparslan
Yigit Alparslan
EMEthan Jacob Moyer
Ethan Jacob Moyer
IIIsamu Mclean Isozaki
Isamu Mclean Isozaki
DSDaniel Schwartz
Daniel Schwartz
ADAdam Dunlop
Adam Dunlop
EKEdward Kim
Edward Kim
In recent years, deep neural networks have had great success in machine learning and pattern recognition. Architecture size for a neural network contributes significantly to the success of neural networks. In this study, we optimize the selection process by investigating different search algorithms to find a neural network architecture size that yields the highest accuracy. We apply binary search on a very well-defined binary classification network search space and compare the results to those of linear search. We also propose how to relax some of the assumptions regarding the data set so that our solution can be generalized to any binary classification problem. We report a 100-fold running time improvement over the naive linear search when we apply the binary search method to our data sets in order to find the best architecture candidate. By finding the optimal architecture for any binary classification problem quickly, we hope that our research contributes to discovering intelligent algorithms for optimizing architecture selection in machine learning.

13 June 2021 in arXiv
Verified
Preprint
Open access
PDF file
YAYigit Alparslan
Yigit Alparslan
EKEdward Kim
Edward Kim
In this paper, we explore the effect of architecture completeness on adversarial robustness. We train models with different architectures on CIFAR-10 and MNIST dataset. For each model, we vary different number of layers and different number of nodes in the layer. For every architecture candidate, we use Fast Gradient Sign Method (FGSM) to generate untargeted adversarial attacks and use adversarial training to defend against those attacks. For each architecture candidate, we report pre-attack, post-attack and post-defense accuracy for the model as well as the architecture parameters and the impact of completeness to the model accuracies.

16 January 2021 in arXiv
Verified
Preprint
Open access
PDF file
YAYigit Alparslan
Yigit Alparslan
EMEthan Jacob Moyer
Ethan Jacob Moyer
IIIsamu Mclean Isozaki
Isamu Mclean Isozaki
DSDaniel Schwartz
Daniel Schwartz
ADAdam Dunlop
Adam Dunlop
EKEdward Kim
Edward Kim
In recent years, deep neural networks have had great success in machine learning and pattern recognition. Architecture size for a neural network contributes significantly to the success of any neural network. In this study, we optimize the selection process by investigating different search algorithms to find a neural network architecture size that yields the highest accuracy. We apply binary search on a very well-defined binary classification network search space and compare the results to those of linear search. We also propose how to relax some of the assumptions regarding the dataset so that our solution can be generalized to any binary classification problem. We report a 100-fold running time improvement over the naive linear search when we apply the binary search method to our datasets in order to find the best architecture candidate. By finding the optimal architecture size for any binary classification problem quickly, we hope that our research contributes to discovering intelligent algorithms for optimizing architecture size selection in machine learning.

12 October 2021
Verified
Thesis
Closed access
YAYigit Can Alparslan
Yigit Can Alparslan
EKEdward Kim
Edward Kim
Numerous recent studies have demonstrated how deep learning (DL) classifiers can be fooled by adversarial examples, in which an attacker adds perturbations to an original sample, causing the classifier to misclassify the sample. Adversarial attacks that render DNNs vulnerable in real life represent a serious threat, given the consequences of improperly functioning autonomous vehicles, malware filters, or biometric authentication systems. Studies in this dissertation explore different techniques to attack against DL models and make them more robust later.