Browsing by Subject "Deep Learning"

Now showing 1 - 3 of 3

Open Access
Covolutional neural networks based on non-euclidean operators
(2018-01) Badawi, Diaa Hisham Jamil
Dot product-based operations in neural net feedforwarding passes are replaced with an ℓ₁-norm inducing operator, which itself is multiplication-free. The neural net, which is called AddNet, retains attributes of ℓ₁-norm based feature extraction schemes such as resilience against outliers. Furthermore, feedforwarding passes can be realized using fewer multiplication operations, which implies energy efficiency. The ℓ₁-norm inducing operator is differentiable w.r.t its operands almost everywhere. Therefore, it is possible to use it in neural nets that are to be trained through standard backpropagation algorithm. AddNet requires scaling (multiplicative) bias so that cost gradients do not explode during training. We present different choices for multiplicative bias: trainable, directly dependent upon the associated weights, or fixed. We also present a sparse variant of that operator, where partial or full binarization of weights is achievable. We ran our experiments over MNIST and CIFAR-10 datasets. AddNet could achieve results that are 0:1% less accurate than a ordinary CNN. Furthermore, trainable multiplicative bias helps the network to converge fast. In comparison with other binary-weights neural nets, AddNet achieves better results even with full or almost full weight magnitude pruning while keeping the sign information after training. As for experimenting on CIFAR-10, AddNet achieves accuracy 5% less than a ordinary CNN. Nevertheless, AddNet is more rigorous against impulsive noise data corruption and it outperforms the corresponding ordinary CNN in the presence of impulsive noise, even at small levels of noise.
Open Access
Deep learning based cell segmentation in histopathological images
(2018-08) Doğan, Deniz
In digital pathology, cell imaging systems allow us to comprehend histopathological events at the cellular level. The first step in these systems is generally cell segmentation, which substantially affects the subsequent steps for an effective and reliable analysis of histopathological images. On the other hand, cell segmentation is a challenging task in histopathological images where there are cells with different pixel intensities and morphological characteristics. The approaches that integrate both pixel intensity and morphological characteristics of cells are likely to achieve successful segmentation results. This thesis proposes a deep learning based approach for a reliable segmentation of cells in the images of histopathological tissue samples stained with the routinely used hematoxylin and eosin technique. This approach introduces two stage convolutional neural networks that employ pixel intensities in the first stage and morphological cell features in the second stage. The proposed TwoStageCNN method is based on extracting cell features, related to cell morphology, from the class labels and posteriors generated in the first stage and uses the morphological cell features in the second stage for the final segmentation. We evaluate the proposed approach on 3428 cells and the experimental results show that our approach yields better segmentation results compared to different segmentation techniques.
Open Access
Improved artificial neural network training with advanced methods
(2018-09) Çatalbaş, Burak
Artificial Neural Networks (ANNs) are used for different machine learning tasks such as classification, clustering etc. They have been utilized in important tasks and offering new services more and more in our daily lives. Learning capabilities of these networks have accelerated significantly since 2000s, with the increasing computational power and data amount. Therefore, research conducted on these networks is renamed as Deep Learning, which emerged as a major research area - not only in the neural networks, but also in the Machine Learning discipline. For such an important research field, the techniques used in the training of these networks can be seen as keys for more successful results. In this work, each part of this training procedure is investigated by using of different and improved - sometimes new - techniques on convolutional neural networks which classify grayscale and colored image datasets. Advanced methods included the ones from the literature such as He-truncated Gaussian initialization. In addition, our contributions to the literature include ones such as SinAdaMax Optimizer, Dominantly Exponential Linear Unit (DELU), He-truncated Laplacian initialization and Pyramid Approach for Max-Pool layers. In the chapters of this thesis, success rates are increased with the addition of these advanced methods accumulatively, especially with DELU and SinAdaMax which are our contributions as upgraded methods. In result, success rate thresholds for different datasets are met with simple convolutional neural networks - which are improved with these advanced methods and reached promising test success increases - within 15 to 21 hours (typically less than a day). Thus, better performances are obtained by those different and improved techniques are shown using well-known classification datasets.