Sharif Digital Repository

The traditional machine learning methods assume that the training data and the test data are drawn from the same distribution (or drawn from the same domain). In practice, in many computer vision applications, this assumption may not hold. Unfortunately, the performance of these methods degrades on dataset drawn from a different domain. Domain adaptation attempts to minimize this degradation caused by distribution mismatch between the training and test data. Domain adaptation tries to adapt a model trainded from one domain to another domain. We focus on supervised domain adaptation method in which limited labeled data is available from the target domain. We propose a new domain adaptation... 

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... 

Detection degradation caused by distribution discrepancy between the training and testing domains is a common problem in object detection systems. The difference between training and testing domains’ distribution mainly happenes because of the different ways of collecting and gathering data. For instance, datasets which have images with different illumination, view point, resolution, background and are obtained by different acquisition systems, have variance in distribution. The solution toward improving the detection rate of the classifier trained on training (source) domain when it is applied on testing (target) domain is to use Domain Adaptation (DA) techniques. One of important branches... 

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... 

Recent advances in deep neural networks have shown significant potential; however, they still face challenges when it comes to non-stationary environments. Continual learning is related to deep neural networks with limited capacity that should perform well on a sequence of tasks. On the other hand, studies have shown that neural networks are sensitive to covariate shifts. But in many cases, the distribution of data varies with time. Domain Adaptation tries to improve the performance of a model on an unlabeled target domain by using the knowledge of other related labeled data coming from a different distribution. Many studies on domain adaptation have optimistic assumptions that are not... 

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... 

In competitive markets where a product or service is provided by multiple providers, as the telecom market, keeping active users is expected to be less expensive than attracting new users. In this regard, first of all, churning should be predicted for active users, and secondly, proper recommendations should be provided to prevent churning. In this thesis, by modeling customer churn as a response to the recommendations, we study the churn prediction and prevention problem as a recommender system. This model enables us to select the best offer for each user to prevent it from churning.Modeling customer churn in a recommender system introduces new challenges, including delay in observing... 

The non-stationary nature of brain activity signals and their many inter-subject differences have created many challenges in the practical applications of emotion recognition based on electroencephalogram (EEG) signals, such as brain-computer interfaces. In such a way, the use of traditional classifiers in classifying these signals leads to a significant decrease in accuracy when applying the classifier to a new subject. Domain Adaptation methods seem to be an effective way to solve this problem by minimizing the difference between the EEG signals of different subjects. But in the basic techniques for domain adaptation, looking at all subjects' data in the same look causes the loss of a part...