Loading...
Search for:
movahederad--mahdieh
0.113 seconds
All-Optical Scalable Multi-stage Interconnection Network for Data Centers
, M.Sc. Thesis Sharif University of Technology ; Koohi, Somayeh (Supervisor)
Abstract
According to the increasing amount of data exchanged among data centers, the need for speeding up and bandwidth and reduced power consumption has been increased. The information show that about 77% of the data is moved into the data centers. On the other hand, 10% of data center’s power consumption is used to data transmission. Improving the interconnection network of data centers can play an important role in reducing power consumption and speeding up. In recent years, optical interconnects have gained attention as a promising solution. Nevertheless, offering an all-optical and efficient architecture is an important issue. In this study, we intend to provide a multi-stage, all-optical...
Test case prioritization using test case diversification and fault-proneness estimations
, Article Automated Software Engineering ; Volume 29, Issue 2 , 2022 ; 09288910 (ISSN) ; Mirian Hosseinabadi, S. H ; Mahdieh, M ; Sharif University of Technology
Springer
2022
Abstract
Regression testing activities greatly reduce the risk of faulty software release. However, the size of the test suites grows throughout the development process, resulting in time-consuming execution of the test suite and delayed feedback to the software development team. This has urged the need for approaches such as test case prioritization (TCP) and test-suite reduction to reach better results in case of limited resources. In this regard, proposing approaches that use auxiliary sources of data such as bug history can be interesting. We aim to propose an approach for TCP that takes into account test case coverage data, bug history, and test case diversification. To evaluate this approach we...
Multi-Modal Distance Metric Learning
, M.Sc. Thesis Sharif University of Technology ; Soleymani, Mahdieh (Supervisor)
Abstract
In many real-world applications, data contain multiple input channels (e.g., web pages include text, images and etc). In these cases, supervisory information may also be available in the form of distance constraints such as similar and dissimilar pairs from user feedbacks. Distance metric learning in these environments can be used for different goals such as retrieval and recommendation. In this research, we used from dual-wing harmoniums to combining text and image modals to a unified latent space when similar-dissimilar pairs are available. Euclidean distance of data represented in this latent space used as a distance metric. In this thesis, we extend the dual-wing harmoniums for...
Unsupervised Domain Adaptation via Representation Learning
, M.Sc. Thesis Sharif University of Technology ; Soleymani, Mahdieh (Supervisor)
Abstract
The existing learning methods usually assume that training and test data follow the same distribution, while this is not always true. Thus, in many cases the performance of these learning methods on the test data will be severely degraded. We often have sufficient labeled training data from a source domain but wish to learn a classifier which performs well on a target domain with a different distribution and no labeled training data. In this thesis, we study the problem of unsupervised domain adaptation, where no labeled data in the target domain is available. We propose a framework which finds a new representation for both the source and the target domain in which the distance between these...
Fabrication and Characterization of Thermoplastic Starch Based Nanocomposite for Bone Scaffold
, M.Sc. Thesis Sharif University of Technology ; Bagheri, Reza (Supervisor)
Abstract
This project aimed to fabricate the bone scaffolds with applying thermoplastic starch-based nano-biocomposites. The starting materials for this scaffold are as follows: thermoplastic starch, ethylene vinyl alcohol as the polymer matrix and nanoforsterite as the ceramic reinforcing phase. Furthermore, vitamin E was used as antioxidant for preserving starch against thermo-mechanical degradations. Likewise, 3D pore structure was developed using azo-dicarbonamide and water in injection moulding process. With blending thermoplastic starch and ethylene vinyl alcohol, some thermoplastic starch’s properties including degradation rate and water absorption were modified. In addition, having...
Deep Learning for Multimodal Data
, M.Sc. Thesis Sharif University of Technology ; Soleymani, Mahdieh (Supervisor)
Abstract
Recent advances in data recording has lead to different modalities like text, image, audio and video. Images are annotated and audio accompanies video. Because of distinct modality statistical properties, shallow methods have been unsuccessful in finding a shared representation which maintains the most information about different modalities. Recently, deep networks have been used for extracting high-level representations for multimodal data. In previous methods, for each modality, one modality-specific network was learned. Thus, high-level representations for different modalities were extracted. Since these high-level representations have less difference than raw modalities, a shared...
Deep Zero-shot Learning
, M.Sc. Thesis Sharif University of Technology ; Soleymani, Mahdieh (Supervisor)
Abstract
In some of object recognition problems, labeled data may not be available for all categories. Zero-shot learning utilizes auxiliary information (also called signatures) describing each category in order to find a classifier that can recognize samples from categories with no labeled instance. On the other hand, with recent advances made by deep neural networks in computer vision, a rich representation can be obtained from images that discriminates different categorizes and therefore obtaining a unsupervised information from images is made possible. However, in the previous works, little attention has been paid to using such unsupervised information for the task of zero-shot learning. In this...
Deep Learning For Recommender Systems
, M.Sc. Thesis Sharif University of Technology ; Soleimani, Mahdieh (Supervisor)
Abstract
Collaborative fltering (CF) is one of the best and widely employed approaches in Recommender systems (RS). This approach tries to fnd some latent features for users and items so it would predict user rates with these features. Early CF methods used matrix factorization to learn users and items latent features. But these methods face cold start as well as sparsity problem. Recent years methods employ side information along with rating matrix to learn users and items latent features. On the other hand, deep learning models show great potential for learning effective representations especially when auxiliary information is sparse. Due to this feature of deep learning, we use deep learning to...
Adversarial Networks for Sequence Generation
, M.Sc. Thesis Sharif University of Technology ; Soleymani, Mahdieh (Supervisor)
Abstract
Lots of essential structures can be modeled as sequences and sequences can be utilized to model the structures like molecules, graphs and music notes. On the other hand, generating meaningful and new sequences is an important and practical problem in different applications. Natural language translation and drug discovery are examples of sequence generation problem. However, there are substantial challenges in sequence generation problem. Discrete spaces of the sequence and challenge of the proper objective function can be pointed out.On the other, the baseline methods suffer from issues like exposure bias between training and test time, and the ill-defined objective function. So, the...
Improving Sampling Efficiency of Probabilistic Graphical Models
, M.Sc. Thesis Sharif University of Technology ; Beigy, Hamid (Supervisor)
Abstract
Deep learning methods have become more popular in the past years. These methods use complex network architectures to model rich, hierarchical datasets. Although most of the research has been centered around Discriminative models, however, recently a lot of research is focused on Deep Generative Models. Two of the pioneering models in this field are Generative Adversarial Networks and Variational Auto-Encoders. In addition, knowing the structure of data helps models to search in a narrower hypothesis space. Most of the structure in datasets are models using Probabilistic Graphical Models. Using this structural information, one can achieve better parameter estimations. In the case of...
Improving Graph Construction for Semi-supervised Learning in Computer Vision Applications
, M.Sc. Thesis Sharif University of Technology ; Rabiee, Hamid Reza (Supervisor)
Abstract
Semi-supervised Learning (SSL) is an extremely useful approach in many applications where unlabeled data can be easily obtained. Graph based methods are among the most studied branches in SSL. Since neighborhood graph is a key component in these methods, we focus on methods of graph construction in this project. Graph construction methods based on Euclidean distance have the common problem of creating shortcut edges. Shortcut edges refer to the edges which connect two nearby points that are far apart on the manifold. Specifically, we show both in theory and practice that using geodesic distance for selecting and weighting edges results in more appropriate neighborhood graphs. We propose an...
Adaptation for Evolving Domains
, M.Sc. Thesis Sharif University of Technology ; Soleymani Baghshah, Mahdieh (Supervisor)
Abstract
Until now many domain adaptation methods have been proposed. A major limitation of almost all of these methods is their assumption that all test data belong to a single stationary target distribution and a large amount of unlabeled data is available for modeling this target distribution. In fact, in many real world applications, such as classifying scene image with gradually changing lighting and spam email identification, data arrives sequentially and the data distribution is continuously evolving. In this thesis, we tackle the problem of adaptation to a continuously evolving target domain that has been recently introduced and propose the Evolving Domain Adaptation (EDA) method to classify...
Multi-label Classification by Considering Label Dependencies
, M.Sc. Thesis Sharif University of Technology ; Soleymani, Mahdieh (Supervisor)
Abstract
In multi-label classification problems each instance can simultaneously have multiple labels. In these problems, in addition to the complexities of the input feature space we encounter the complexities of output label space. In the multi-label classification problems, there are dependencies between different labels that need to be considered. Since the dimensionality of the label space in real-world applications can be (very) high, most methods which explicitly model these dependencies are ineffective in practice and recently those methods that transform the label space into a latent space have received attention. A class of these methods which uses output space dimension reduction, first...
Answering Questions about Image Contents by Deep Networks
, M.Sc. Thesis Sharif University of Technology ; Soleymani Baghshah, Mahdieh (Supervisor)
Abstract
Due to the recent advances in the learning of multimodal data, humans tend to use computer systems in order to solve more complex problems. One of them is Visual Question Answering (VQA), where the goal is finding the answer of a question asked about the visual contents of a given image. This is an interdisciplinary problem between the areas of Computer Vision, Natural Language Processing and Reasoning. Because of recent achievements of Deep Neural Networks in these areas, recent works used them to address the VQA task. In this thesis, three different methods have been proposed which adding each of them to existing solutions to the VQA problem can improve their results. First method tries to...
Adversarial Robustness of Deep Neural Networks in Text Domain
, M.Sc. Thesis Sharif University of Technology ; Soleymani Baghshah, Mahdieh (Supervisor)
Abstract
In recent years, neural networks have been widely used in most machine learning domains. However, it has been shown that these networks are vulnerable to adversarial examples. adversarial examples are small and imperceptible perturbations applied to the input which lead to producing wrong output and thus, fooling the network. This will become an important issue in security related applications of deep neural networks, such as self-driving cars and medical diagnostics. Since, in the wort-case scenario, even human lives could be threatened. Although, many works have focused on crafting adversarial examples for image data, only a few studies have been done on textual data due to the existing...
Conditional Text Generation with Neural Networks
, M.Sc. Thesis Sharif University of Technology ; Soleymani, Mahdieh (Supervisor)
Abstract
By the improvement of machine learning methods specially the Deep Learning in the last decade, there were expanding usage of these methods in Language Modeling task. As the essence of a language model is more basic, recently huge networks are trained with language model objective but fine-tuned on target tasks such as Question Answering, Sentiment Analysis and etc. which is a promising sign of its importance and usage in even other NLP tasks. However, this task still has severe problems. The Teacher Forcing based methods, suffer from the so-called exposure bias problem which is due to the train/test procedure discrepancy. Some solutions such as using Reinforcement Learning which has high...
Cancer Prediction Using cfDNA Methylation Patterns With Deep Learning Approach
, M.Sc. Thesis Sharif University of Technology ; Soleymani Baghshah, Mahdieh (Supervisor)
Abstract
Liquid biopsy includes information about the progress of the tumor, the effectiveness of the treatment and the possibility of tumor metastasis. This type of biopsy obtains this information by doing diagnosis and enumerating genetic variations in cells and cell-free DNA (cfDNA). Only a small fraction of cfDNA which might be free circulation tumor DNA (ctDNA) fragments, has mutations and is usually identified by epigenetic variations. On the other hand, the use of liquid biopsy has decreased, and tumors in the final stages are often untreatable due to the low accuracy in prediction of cancer. In this research, the aim is to predict cancer using cfDNA methylation patterns. We obtain these...
3D Medical Images Segmentation by Effective Use of Unlabeled Data
, M.Sc. Thesis Sharif University of Technology ; Soleymani Baghshah, Mahdieh (Supervisor)
Abstract
Image segmentation in medical imaging, as one of the most important branches of medical image analysis, often faces the challenge of limited labeled data for application in deep learning methods. The high cost of data collection and the need for expertise in image segmentation, particularly in three-dimensional images such as MRI and CT or sequence images like CMR, have all contributed to this problem, even for popular networks like U-Net, which struggle to achieve high accuracy. As a result, research efforts have focused on semi-supervised learning approaches, weakly supervised learning, as well as multi-instance learning in medical image segmentation. Unfortunately, each of these methods...
Deep Learning Approach for Domain Adaptation
, M.Sc. Thesis Sharif University of Technology ; Soleymani Baghshah, Mahdieh (Supervisor)
Abstract
A predefined assumption in many learning algorithms is that the training and test data must be in thesame feature space and have the same distribution.However, this assumption may not hold in all of these algorithms and in the real world there might be difference between the source and the targer domian, whether in the feature space or the distribution. Moreover, there might be a few number of labled data of the target domain which causes difficulty in learning an accurate classifier. In such cases, transferring knowledge can be useful if can be done successfully and transfer learning was introduced for this purpose. Domain Adaptation is one of the transfer leaning problems that assume some...
Few-Shot Semantic Segmentaion Using Meta-Learning
,
M.Sc. Thesis
Sharif University of Technology
;
Soleymani Baghshah, Mahdieh
(Supervisor)
Abstract
Despite recent advancements in deep learning methods, these methods rely on a huge amount of training data to work. Recently the problem of solving classification and recently semantic segmentation problems with a few training data have gained attention to tackle this issue. In this research, we propose a meta-learning method by combining optimization-based and prototypical approaches in which a small portion of parameters are optimized with task-specific initialization. In addition to this and designing other parts of the method, we propose a new approach to use query data as an unlabeled sample to enhance task-specific learning. Alongside the mentioned method, we propose an approach to use...