Sharif Digital Repository

In machine learning, classification is of great importance. Unlike the traditional single-label classification in which one instance can have only one label, in multi-label classification tasks, an instance can be associated with a set of labels. Multi-label classifiers have to address many problems including: considering correlations between labels, handling large-scale datasets with many instances and a large set of labels, and having only a fraction of valid label assignments in the training set. To tackle datasets with a large set of labels, recently embedding-based methods have been proposed which seek to represent the label assignments in an intermediate space. Subsequently, given the... 

In recent years, The Web has become an environment for sharing the knowledge of users, which as its popular examples can refer to question and answering communities. In QA communities such as Quora, StackOverflow and Yahoo! Answers, People exchange information through online questions and answers. Thus, These communities have become valuable resources of information with the participation of users. Several issues have been raised in these communities. One of the issues raised in these communities is to automatically fnd similar questions to a question and then fnd the answers that are related to it among the available answers. Other issues raised in these communities include choosing the... 

The goal of this project is the development of a control algorithm for a flock of non-holonomic aerial agents. For this purpose,the swarm architecture having some unique features such as robustness, flexibility, and scalability is utilized. Swarm is defined as a group of simple agents having local interactions between themselves and the environmentwhich shows an unpredictable emergent behavior.Behavior based control which is inspired from the animal behaviors is employed to control the swarm of mobile agents. Accordingly, the necessary behaviors which are distance adjustment, velocity agreement, and virtual leader tracking together with a fuzzy coordinator are designed. In this study, in... 

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... 

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... 

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... 

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... 

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... 

The development of smart meters enables gathering and analysis of a large amount of data about electrical energy consumption in electric power distribution systems. This data and the obtained behavioral patterns of customers have a wide variety of applications. To name a few, classification of customers based on their consumption patterns, damaged smart meter identification, non-technical loss identification and measuring participation rate of customers in demand response programs are among the applications. So far, many studies have been done for consumption pattern identification. However, abnormality detection in electric energy consumption has captured growing attention due to the... 

Collapsible soils such as loess, which are naturally nearly dry or unsaturated, are problematic soils that experience significant decrease in volume when they are subjected to increasing moisture under loading. This type of soils are present in some parts of Iran such as province of Golestan. Most of the researches to date has tended to focus on measuring the values of collapse using conventional double oedometer. However, the study of hydromechanical behavior of this type of soils considering the effect of initial shear stress using unsaturated triaxial device has been rarely investigated by the researchers. The study on the unsaturated behavior of collapsible soils has started at Sharif... 

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... 

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...