6 sonuçlar
Arama Sonuçları
Listeleniyor 1 - 6 / 6
Yayın Malaria parasite detection with deep transfer learning(IEEE, 2018-12-06) Var, Esra; Tek, Faik BorayThis study aims to automatically detect malaria parasites (Plasmodium sp) on images taken from Giemsa stained blood smears. Deep learning methods provide limited performance when sample size is low. In transfer learning, visual features are learned from large general data sets, and problem-specific classification problem can be solved successfully in restricted problem specific data sets. In this study, we apply transfer learning method to detect and classify malaria parasites. We use a popular pre-trained CNN model VGG19. We trained the model for 20 epoch on 1428 P Vivax, 1425 P Ovule, 1446 E Falciparum, 1450 P Malariae and 1440 non-parasite samples. The transfer learning model achieves %80, %83, %86, %75 precision and 83%, 86%, 86%, 79% f-measure on 19 test images.Yayın Unreasonable effectiveness of last hidden layer activations for adversarial robustness(Institute of Electrical and Electronics Engineers Inc., 2022) Tuna, Ömer Faruk; Çatak, Ferhat Özgür; Eskil, Mustafa TanerIn standard Deep Neural Network (DNN) based classifiers, the general convention is to omit the activation function in the last (output) layer and directly apply the softmax function on the logits to get the probability scores of each class. In this type of architectures, the loss value of the classifier against any output class is directly proportional to the difference between the final probability score and the label value of the associated class. Standard White-box adversarial evasion attacks, whether targeted or untargeted, mainly try to exploit the gradient of the model loss function to craft adversarial samples and fool the model. In this study, we show both mathematically and experimentally that using some widely known activation functions in the output layer of the model with high temperature values has the effect of zeroing out the gradients for both targeted and untargeted attack cases, preventing attackers from exploiting the model's loss function to craft adversarial samples. We've experimentally verified the efficacy of our approach on MNIST (Digit), CIFAR10 datasets. Detailed experiments confirmed that our approach substantially improves robustness against gradient-based targeted and untargeted attack threats. And, we showed that the increased non-linearity at the output layer has some ad-ditional benefits against some other attack methods like Deepfool attack.Yayın Animal sound classification using a convolutional neural network(IEEE, 2018-12-06) Şaşmaz, Emre; Tek, Faik BorayIn this paper, we investigate the problem of animal sound classification using deep learning and propose a system based on convolutional neural network architecture. As the input to the network, sound files were preprocessed to extract Mel Frequency Cepstral Coefficients (MFCC) using LibROSA library. To train and test the system we have collected 875 animal sound samples from an online sound source site for 10 different animal types. We report classification confusion matrices and the results obtained by different gradient descent optimizers. The best accuracy of 75% was obtained by Nesterov-accelerated Adaptive Moment Estimation (Nadam).Yayın Uzaktan algılanan görüntülerde bina yoğunluğu kestirimi için derin öğrenme(Institute of Electrical and Electronics Engineers Inc., 2019-09) Süberk, Nilay Tuğçe; Ateş, Hasan FehmiBu bildiri, derin öğrenme yöntemleri uygulayarak uzaktan algılamalı optik görüntülerde bina yoğunluğunun noktasal olarak kestirilmesi ile ilgilidir. Bu çalışma kapsamında, evrişimsel sinir ağına (ESA) dayalı derin öğrenme yöntemlerine başvurulmuştur. Önceden eğitilmiş, VGG-16 ve FCN-8s derin mimarileri bu probleme uyarlanmış ve ince ayar verilerek eğitilmiştir. Kestirilen değerler yerleşim bölgelerinde bina yoğunluk haritası oluşturmak için kullanılmıştır. Her iki mimarinin karşılaştırmalı benzetim sonuçları, güdümlü eğitim için binaları gösteren detaylı haritalara ihtiyaç duyulmadan hassas yoğunluk kestirimi yapılabileceğini göstermektedir.Yayın Assessing ChatGPT's accuracy in dyslexia inquiry(Institute of Electrical and Electronics Engineers Inc., 2024) Eroğlu, Günet; Harb, Mhd Raja AbouDyslexia poses challenges in accessing reliable information, crucial for affected individuals and their families. Leveraging chatbot technology offers promise in this regard. This study evaluates the OpenAI Assistant's precision in addressing dyslexia-related inquiries. Three hundred questions commonly posed by parents were categorized and presented to the Assistant. Expert evaluation of responses, graded on accuracy and completeness, yielded consistently high scores (median=5). Descriptive questions scored higher (average=4.9568) than yes/no questions (average=4.8957), indicating potential response challenges. Statistical analysis highlighted the significance of question specificity in response quality. Despite occasional difficulties, the Assistant demonstrated adaptability and reliability in providing accurate dyslexia-related information.Yayın El yazısı rakam sınıflandırması için gözetimsiz benzerlik tabanlı evrişimler(Institute of Electrical and Electronics Engineers Inc., 2022) Erkoç, Tuğba; Eskil, Mustafa TanerEffective training of filters in Convolutional Neural Networks (CNN) ensures their success. In order to achieve good classification results in CNNs, filters must be carefully initialized, trained and fine-tuned. We propose an unsupervised method that allows the discovery of filters from the given dataset in a single epoch without specifying the number of filters hyper-parameter in convolutional layers. Our proposed method gradually builds the convolutional layers by a discovery routine that extracts a number of features that adequately represent the complexity of the input domain. The discovered filters represent the patterns in the domain, so they do not require any initialization method or backpropagation training for fine tuning purposes. Our method achieves 99.03% accuracy on MNIST dataset without applying any data augmentation techniques.
