Browsing by Subject "Collaborative learning"
Now showing 1 - 3 of 3
Results Per Page
Sort Options
Item Open Access The effect of collaborative activities on college-level EFL students’ learner autonomy in the Turkish context(Bilkent University, 2016-06) Turan Öztürk, DemetOne of the most fundamental aims of education in EFL context has been fostering learner autonomy. So far, various studies have been conducted and teaching practices have been put to use in order to develop learners’ autonomous learning skills. One of these practices could be changing the traditional methods in language teaching in Turkish educational system into student-centered ones. Such a practice could create opportunities for students to study together and allow them to learn from each other by improving their sense of responsibility and take control of their own learning. Therefore, the purpose of this study is to investigate the effect of collaborative activities on college-level EFL students’ learner autonomy in the Turkish context. It also aims to find out the students’ and the instructor’s perceptions of collaborative activities on learner autonomy development. To achieve this aim, both quantitative and qualitative data were collected with the help of a Learner Autonomy questionnaire, index cards filled out by the students, the One of the most fundamental aims of education in EFL context has been fostering learner autonomy. So far, various studies have been conducted and teaching practices have been put to use in order to develop learners’ autonomous learning skills. One of these practices could be changing the traditional methods in language teaching in Turkish educational system into student-centered ones. Such a practice could create opportunities for students to study together and allow them to learn from each other by improving their sense of responsibility and take control of their own learning. Therefore, the purpose of this study is to investigate the effect of collaborative activities on college-level EFL students’ learner autonomy in the Turkish context. It also aims to find out the students’ and the instructor’s perceptions of collaborative activities on learner autonomy development. To achieve this aim, both quantitative and qualitative data were collected with the help of a Learner Autonomy questionnaire, index cards filled out by the students, the instructor’s journal, and an interview with the instructor. Two groups of 40 students in total from the preparatory program of Niğde University School of Foreign Languages were appointed as an experimental and a control group. The learner autonomy questionnaire was conducted as both pre-test and post-test in both groups, before and after the collaborative learning treatment in the experimental group, in order to detect any possible change in students’ learner autonomy level. Quantitative data from the questionnaires were analyzed by using Wilcoxon Matched Groups test and Mann-Whitney U Test. Qualitative data gathered from index cards, the journal and the interview were analyzed with the use of content analysis. The results of the quantitative data analysis revealed that, after the treatment, there was a statistically significant difference between the groups in terms of their autonomy level; the students in the experimental group scored higher than those in the control group, which implies they showed more autonomous skills than the control group. The results of the qualitative data analysis indicated that participants’ perceptions were highly positive about the collaborative activities. They revealed that collaborative activities created a positive environment in the classroom and allowed them to learn from each other and gain a sense of responsibility. The course instructor was also in favor of the collaborative activities as they had various benefits for her teaching. These overall results suggested that collaborative learning practices could be implemented to help the students increase their learner autonomy level in the Turkish EFL context.Item Open Access Key protected classification for collaborative learning(Elsevier, 2020) Sarıyıldız, Mert Bülent; Cinbiş, R. G.; Ayday, ErmanLarge-scale datasets play a fundamental role in training deep learning models. However, dataset collection is difficult in domains that involve sensitive information. Collaborative learning techniques provide a privacy-preserving solution, by enabling training over a number of private datasets that are not shared by their owners. However, recently, it has been shown that the existing collaborative learning frameworks are vulnerable to an active adversary that runs a generative adversarial network (GAN) attack. In this work, we propose a novel classification model that is resilient against such attacks by design. More specifically, we introduce a key-based classification model and a principled training scheme that protects class scores by using class-specific private keys, which effectively hide the information necessary for a GAN attack. We additionally show how to utilize high dimensional keys to improve the robustness against attacks without increasing the model complexity. Our detailed experiments demonstrate the effectiveness of the proposed technique. Source code will be made available at https://github.com/mbsariyildiz/key-protected-classification.Item Open Access Learning efficient visual embedding models under data constraints(Bilkent University, 2019-09) Sarıyıldız, Mert BülentDeep learning models require large-scale datasets to learn rich sets of low and mid-level patterns and high-level semantics. Therefore, given a high-capacity neural network, one way to improve the performance of a model is increasing the size of the dataset which the model is trained over on. Considering that it is easy to get the amount of computational power required to train a network, data becomes a serious bottleneck in scaling up the existing machine learning pipelines. In this thesis, we look into two main data bottlenecks that rise in computer vision applications: I. the difficulty of finding training data for diverse sets of object categories, II. the complication of utilizing data containing sensitive user information for the purpose of training neural network models. To address these issues, we study zero-shot learning and decentralized learning schemes, respectively. Zero-shot learning (ZSL) is one of the most promising problems where substantial progress can potentially be achieved through unsupervised learning, due to distributional differences between supervised and zero-shot classes. For this reason, several works investigate the incorporation of discriminative domain adaptation techniques into ZSL, which, however, lead to modest improvements in ZSL accuracy. In contrast, we propose a generative model that can naturally learn from unsupervised examples, and synthesize training examples for unseen classes purely based on their class embeddings, and therefore, reduce the zero-shot learning problem into a supervised classification task. The proposed approach consists of two important components: I. a conditional Generative Adversarial Network that learns to produce samples that mimic the characteristics of unsupervised data examples, and II. the Gradient Matching (GM) loss that measures the quality of the gradient signal obtained from the synthesized examples. Using our GM loss formulation, we enforce the generator to produce examples from which accurate classifiers can be trained. Experimental results on several ZSL benchmark datasets show that our approach leads to significant improvements over the state of the art in generalized zero-shot classification. Collaborative learning techniques provide a privacy-preserving solution, by enabling training over a number of private datasets that are not shared by their owners. However, recently, it has been shown that the existing collaborative learning frameworks are vulnerable to an active adversary that runs a generative adversarial network (GAN) attack. In this work, we propose a novel classification model that is resilient against such attacks by design. More specifically, we introduce a key-based classification model and a principled training scheme that protects class scores by using class-specific private keys, which effectively hides the information necessary for a GAN attack. We additionally show how to utilize high dimensional keys to improve the robustness against attacks without increasing the model complexity. Our detailed experiments demonstrate the effectiveness of the proposed technique.