7 sonuçlar
Arama Sonuçları
Listeleniyor 1 - 7 / 7
Yayın Learning filter scale and orientation in convolutional neural networks(Işık Üniversitesi, 2019-04-02) Çam, İlker; Tek, Faik Boray; Işık Üniversitesi, Fen Bilimleri Enstitüsü, Bilgisayar Mühendisliği Yüksek Lisans ProgramıConvolutional neural networks have many hyper-parameters such as filter size, number of filters, and pooling size, which require manual tuning. Though deep stacked structures are able to create multi-scale and hierarchical representations, manually fixed filter sizes limit the scale of representations that can be learned in a single convolutional layer. Can we adaptively learn to scale the filters on training time? Proposed adaptive filter model can learn the scale and orientation parameters of filters using backpropagation. Therefore, in a single convolution layer, we can create filters of diffierent scale and orientation that can adapt to small or large features and objects. The proposed model uses a relatively large base size (grid) for filters. In the grid, a differentiable function acts as an envelope for the filters. The envelope function guides efective filter scale and shape/orientation by masking the filter weights before the convolution. Therefore, only the weights in the envelope are updated during training. In this work, we employed a multivariate (2D) Gaussian as the envelope function and showed that it can grow, shrink, or rotate by updating its covariance matrix during backpropagation training. We tested the model with its basic settings to show the collaboration of weight matrix with envelope function is possible. A deeper architecture was used to show the performance on deeper and wider networks. We tested the new filter model on MNIST, MNIST-cluttered, and CIFAR-10 datasets. Compared the results with the networks that used conventional convolution layers. The results demonstrate that the new model can effectively learn and produce filters of different scales and orientations in a single layer. Moreover, the experiments show that the adaptive convolution layers perform equally; or better, especially when data includes objects of varying scale and noisy backgrounds.Yayın A new approach for named entity recognition(IEEE, 2017) Ertopçu, Burak; Kanburoğlu, Ali Buğra; Topsakal, Ozan; Açıkgöz, Onur; Gürkan, Ali Tunca; Özenç, Berke; Çam, İlker; Avar, Begüm; Ercan, Gökhan; Yıldız, Olcay TanerMany sentences create certain impressions on people. These impressions help the reader to have an insight about the sentence via some entities. In NLP, this process corresponds to Named Entity Recognition (NER). NLP algorithms can trace a lot of entities in the sentence like person, location, date, time or money. One of the major problems in these operations are confusions about whether the word denotes the name of a person, a location or an organisation, or whether an integer stands for a date, time or money. In this study, we design a new model for NER algorithms. We train this model in our predefined dataset and compare the results with other models. In the end we get considerable outcomes in a dataset containing 1400 sentences.Yayın Etkileşimli öğrenme ile akciğer tomografi hacim taramalarında nodül tespiti(Institute of Electrical and Electronics Engineers Inc., 2016-06-20) Çam, İlker; Tek, Faik BorayBu bildiride akciğer BT taramalarında otomatik nodül tespiti yapmak üzere geliştirdigimiz yeni ve özgün bir yöntem sunulmaktadır. Önerdiğimiz yöntem, akciğer organına ve belirli bir nodül tipine bağlı kalmaksızın genelleştirilmiş bir yaklaşım sunmaktadır. Böylelikle akciğer bölütlemesine ihtiyaç duymamaktadır. Düşük doz radyasyonlu ve çeşitli tipte (katı ve kırık cam görünümlü, yüzeye ve damara ilişik) 10 mm’den küçük nodüllerden oluşan zorlu bir tarama kümesinde (Anode09) sınamalar yapılmıştır. Tarama başına ortalama 8 yanlış tespit için nodül tespit duyarlılığı %52’dir. Yarışmada ilk altıya giren algoritmalarla karşılaştırılabilir düzeydedir.Yayın Shallow parsing in Turkish(IEEE, 2017) Topsakal, Ozan; Açıkgöz, Onur; Gürkan, Ali Tunca; Kanburoğlu, Ali Buğra; Ertopçu, Burak; Özenç, Berke; Çam, İlker; Avar, Begüm; Ercan, Gökhan; Yıldız, Olcay TanerIn this study, shallow parsing is applied on Turkish sentences. These sentences are used to train and test the per-formances of various learning algorithms with various features specified for shallow parsing in Turkish.Yayın Adaptive convolution kernel for artificial neural networks(Academic Press Inc., 2021-02) Tek, Faik Boray; Çam, İlker; Karlı, DenizMany deep neural networks are built by using stacked convolutional layers of fixed and single size (often 3 × 3) kernels. This paper describes a method for learning the size of convolutional kernels to provide varying size kernels in a single layer. The method utilizes a differentiable, and therefore backpropagation-trainable Gaussian envelope which can grow or shrink in a base grid. Our experiments compared the proposed adaptive layers to ordinary convolution layers in a simple two-layer network, a deeper residual network, and a U-Net architecture. The results in the popular image classification datasets such as MNIST, MNIST-CLUTTERED, CIFAR-10, Fashion, and ‘‘Faces in the Wild’’ showed that the adaptive kernels can provide statistically significant improvements on ordinary convolution kernels. A segmentation experiment in the Oxford-Pets dataset demonstrated that replacing ordinary convolution layers in a U-shaped network with 7 × 7 adaptive layers can improve its learning performance and ability to generalize.Yayın All-words word sense disambiguation for Turkish(IEEE, 2017) Açıkgöz, Onur; Gürkan, Ali Tunca; Ertopçu, Burak; Topsakal, Ozan; Özenç, Berke; Kanburoğlu, Ali Buğra; Çam, İlker; Avar, Begüm; Ercan, Gökhan; Yıldız, Olcay TanerIdentifying the sense of a word within a context is a challenging problem and has many applications in natural language processing. This assignment problem is called word sense disambiguation(WSD). Many papers in the literature focus on English language and data. Our dataset consists of 1400 sentences translated to Turkish from the Penn Treebank Corpus. This paper seeks to address and discuss 6 different feature extraction methods and its classification performances using C4.5, Random Forests, Rocchio, Naive Bayes, KNN, Linear and multilayer Perceptron. This paper calls into question how the described features perform on a morphologically rich language (Turkish) with several classifiers.Yayın Odaklanan nöron(IEEE, 2017-06-27) Çam, İlker; Tek, Faik BorayGeleneksel yapay sinir ağında topoloji eğitim sırasında değişebilecek esnekliğe sahip değildir. Ağda her bir nöron ve bağımsız bağlantı katsayıları çözüm işlevinin bir parçasıdır. Bu bildiride önerdiğimiz odaklanabilir nöron birbirine bağımlı katsayıların çekildiği bir odaklayıcı işlevden yararlanır. Nöron odak pozisyonu ve açıklığını değiştirerek aktivasyon topladığı nöronları değiştirebilir. Bu özelliği sayesinde esnek ve dinamik bir ağ topolojisi oluşturabilir ve standart geriye yayılım algoritmasıyla eğitilebilir. Yapılan deneylerde odaklanabilir nöronlarla kurulan bir ağ yapısının, tümüyle bağlı yapay sinir ağına göre daha yüksek başarı elde ettiği gözlenmiştir.
