7 sonuçlar
Arama Sonuçları
Listeleniyor 1 - 7 / 7
Yayın Exploiting epistemic uncertainty of the deep learning models to generate adversarial samples(Cornell Univ, 2021-02-13) Tuna, Ömer Faruk; Çatak, Ferhat Özgür; Eskil, Mustafa TanerDeep neural network architectures are considered to be robust to random perturbations. Nevertheless, it was shown that they could be severely vulnerable to slight but carefully crafted perturbations of the input, termed as adversarial samples. In recent years, numerous studies have been conducted in this new area called "Adversarial Machine Learning" to devise new adversarial attacks and to defend against these attacks with more robust DNN architectures. However, almost all the research work so far has been concentrated on utilising model loss function to craft adversarial examples or create robust models. This study explores the usage of quantified epistemic uncertainty obtained from Monte-Carlo Dropout Sampling for adversarial attack purposes by which we perturb the input to the areas where the model has not seen before. We proposed new attack ideas based on the epistemic uncertainty of the model. Our results show that our proposed hybrid attack approach increases the attack success rates from 82.59% to 85.40%, 82.86% to 89.92% and 88.06% to 90.03% on MNIST Digit, MNIST Fashion and CIFAR-10 datasets, respectively.Yayın Cohomologies and generalized derivation extensions of n-Lie algebras(Cornell Univ, 2021-04-18) Ateşli, Begüm; Esen, Oğul; Sütlü, SerkanA cohomology theory, associated to a n-Lie algebra and a representation space of it, is introduced. It is observed that this cohomology theory is qualified to encode the generalized derivation extensions, and that it coincides, for n = 3, with the known cohomology of n-Lie algebras. The abelian extensions and infinitesimal deformations of n-Lie algebras, on the other hand, are shown to be characterized by the usual cohomology of n-Lie algebras. Furthermore, the Hochschild-Serre spectral sequence of the Lie algebra cohomology is upgraded to the level of n-Lie algebras, and is applied to the cohomology of generalized derivation extensions.Yayın Quantum van Est isomorphism(Cornell Univ, 2022-05-07) Kaygun, Atabey; Sütlü, SerkanMotivated by the fact that the Hopf-cyclic (co)homology of the quantized algebras of functions and quantized universal enveloping algebras are the correct analogues of the Lie algebra and Lie group (co)homologies, we hereby construct three van Est type isomorphisms between the Hopf-cyclic (co)homologies of Lie groups and Lie algebras, and their quantum groups and corresponding enveloping algebras, both in h-adic and q-deformation frameworks.Yayın Unsupervised textile defect detection using convolutional neural networks(Cornell Univ, 2023-11-30) Koulali, Imane; Eskil, Mustafa TanerIn this study, we propose a novel motif-based approach for unsupervised textile anomaly detection that combines the benefits of traditional convolutional neural networks with those of an unsupervised learning paradigm. It consists of five main steps: preprocessing, automatic pattern period extraction, patch extraction, features selection and anomaly detection. This proposed approach uses a new dynamic and heuristic method for feature selection which avoids the drawbacks of initialization of the number of filters (neurons) and their weights, and those of the backpropagation mechanism such as the vanishing gradients, which are common practice in the state-of-the-art methods. The design and training of the network are performed in a dynamic and input domain-based manner and, thus, no ad-hoc configurations are required. Before building the model, only the number of layers and the stride are defined. We do not initialize the weights randomly nor do we define the filter size or number of filters as conventionally done in CNN-based approaches. This reduces effort and time spent on hyperparameter initialization and fine-tuning. Only one defect-free sample is required for training and no further labeled data is needed. The trained network is then used to detect anomalies on defective fabric samples. We demonstrate the effectiveness of our approach on the Patterned Fabrics benchmark dataset. Our algorithm yields reliable and competitive results (on recall, precision, accuracy and f1- measure) compared to state-of-the-art unsupervised approaches, in less time, with efficient training in a single epoch and a lower computational cost.Yayın On twisted torsion of compact 3-manifolds(Cornell Univ, 2024-08-20) Erdal, Esma DiricanLet M be a 3-manifold with connected non-vacuos boundary which is not spherical. Assume that N is another 3-manifold with vacuous boundary and N∗ is the 3-manifold obtained by removing from N the interior of a 3-cell. In the present paper, we find a relationship between the multiplicative property of the twisted Reidemeister torsion and the connected sum operation on these manifolds in order to understand their topology and geometry.Yayın Intelligent health monitoring in 6G networks: machine learning-enhanced VLC-based medical body sensor networks(MDPI, 2025-04-30) Antaki, Bilal; Dalloul, Ahmed Hany; Miramirkhani, FarshadRecent advances in Artificial Intelligence (AI)-driven wireless communication demand innovative Sixth Generation (6G) solutions, particularly in hospitals where reliability and secure communication are crucial. Visible Light Communication (VLC) leverages existing lighting systems to deliver high data rates while mitigating electromagnetic interference. However, VLC systems in medical settings face fluctuating signal strength and dynamic channel conditions due to patient movement, necessitating advanced optimization techniques. This paper employs a site-specific ray tracing technique in Medical Body Sensor Networks (MBSNs) channel modeling within hospital scenarios to derive channel impulse responses (CIRs) and model path loss (PL) and Root Mean Square (RMS) delay spread in two distinct hospital settings. In the first section, we evaluate Machine Learning (ML)-based adaptive modulation in VLC-enabled MBSNs and introduce a Q-learning technique enabling real-time adaptation without prior environmental knowledge. In the second section, we propose a Long Short Term Memory (LSTM) based approach to estimate PL and RMS delay spread in dynamic hospital environments. The Q-learning method consistently achieved the target symbol error rate (SER), though spectral efficiency (SE) was sometimes lower than optimal due to quantization limits and a cautious approach near the SER threshold. For LSTM-based channel estimation algorithm, simulation studies show that in the Intensive Care Unit (ICU) ward scenario, D1 has the highest Root Mean Squared Error (RMSE) for estimated path loss (1.6797 dB) and RMS delay spread (1.0567 ns), whereas in the Family-Type Patient Rooms (FTPR) scenario, D3 exhibits the highest RMSE for estimated path loss (1.0652 dB) and RMS delay spread (0.7657 ns).Yayın Variational self-supervised learning(Cornell Univ, 2025-04-06) Yavuz, Mehmet Can; Yanıkoğlu, BerrinWe present Variational Self-Supervised Learning (VSSL), a novel framework that combines variational inference with self-supervised learning to enable efficient, decoder-free representation learning. Unlike traditional VAEs that rely on input reconstruction via a decoder, VSSL symmetrically couples two encoders with Gaussian outputs. A momentum-updated teacher network defines a dynamic, data-dependent prior, while the student encoder produces an approximate posterior from augmented views. The reconstruction term in the ELBO is replaced with a cross-view denoising objective, preserving the analytical tractability of Gaussian KL divergence. We further introduce cosine-based formulations of KL and log-likelihood terms to enhance semantic alignment in high-dimensional latent spaces. Experiments on CIFAR-10, CIFAR-100, and ImageNet-100 show that VSSL achieves competitive or superior performance to leading self-supervised methods, including BYOL and MoCo V3. VSSL offers a scalable, probabilistically grounded approach to learning transferable representations without generative reconstruction, bridging the gap between variational modeling and modern self-supervised techniques.
