Sharif Digital Repository

A new algorithm for learning jointly reconstructive and discriminative dictionaries for sparse representation (SR) is presented. While in a usual dictionary learning algorithm like K-SVD only the reconstructive aspect of the sparse representations is considered to learn a dictionary, in our proposed algorithm, which we call K-LDA, the discriminative aspect of the sparse representations is also addressed. In fact, K-LDA is an extension of K-SVD in the case that the class informations (labels) of the training data are also available. K-LDA takes into account these information in order to make the sparse representations more discriminate. It makes a trade-off between the amount of... 

This study aims to identify the learning orientations and language learning strategies of the students, to determine whether there are any significant differences in the motivational orientations and language learning strategies preferences between male and female learners, and investigate whether there is a relationship between students' motivational orientations and strategy preferences. A total of 206 intermediate level students who studied in English in private language institutes were asked to complete two questionnaires. One was used to identify students' motivational orientations and the other was used to identify students' learning strategies. Statistical analyses demonstrated that... 

Distance metric learning is a powerful approach to deal with the clustering problem with side information. For semi-supervised clustering, usually a set of pairwise similarity and dissimilarity constraints is provided as supervisory information. Although some of the existing methods can use both equivalence (similarity) and inequivalence (dissimilarity) constraints, they are usually limited to learning a global Mahalanobis metric (i.e., finding a linear transformation). Moreover, they find metrics only according to the data points appearing in constraints, and cannot utilize information of other data points. In this paper, we propose a probabilistic metric learning algorithm which uses... 

The model of emotional masks is a newly developed AI paradigm based on Minsky's model of emotional mind in his recent book "The emotion machine". The model takes a resource management approach toward modeling the mind and views different processes of mind as resources that need to be managed. In the present work an intelligent controller (SCELIC) is developed based on the model of emotional masks. SCELIC is a model free controller which advantages from several learning tasks. Multiple learnings and adaptive structure make it a powerful adaptive and self-learning tool that performs the tasks of system identification and control in parallel. Although the test-bed considered here is a nonlinear... 

A repeated inflation-unemployment game within the linear-quadratic frame-work of Barro and Gordon is studied assuming that the government would like to cheat optimally and the finite heterogeneous population of private agents attempts to learn the government's targets using a reinforcement learning algorithm. Private agents are heterogeneous in their initial expectations of inflation rate but are assumed to utilize an identical anticipatory reinforcement learning process, namely Q-learning. In our heterogeneous setting, the only way for the private agents to achieve a zero value for their loss function, is for all of them to correctly anticipate the Nash equilibrium. It is of particular... 

In the past few years, Iranian universities have embarked to use e-learning tools and technologies to extend and improve their educational services. After a few years of conducting e-learning programs a debate took place within the executives and managers of the e-learning institutes concerning which activities are of the most influence on the learning progress of online students. This research is aimed to investigate the impact of a number of e-learning activities on the students' learning development. The results show that participation in virtual classroom sessions has the most substantial impact on the students' final grades. This paper presents the process of applying data mining... 

The ability to accurately classify temporal relation between events is an important task for a large number of natural language processing applications such as Question Answering (QA), Summarization, and Information Extraction. This paper presents a weakly-supervised machine learning approach for classification of temporal relation between events. In the first stage, the algorithm learns a general classifier from an annotated corpus. Then, it applies the hypothesis of "one type of temporal relation per discourse" and expands the scope of "discourse" from a single document to a cluster of topically-related documents. By combining the global information of such a cluster with local decisions... 

In this paper, we propose a novel density-based fuzzy clustering algorithm based on Active Learning Method (ALM), which is a methodology of soft computing inspired by some hypotheses claiming that human brain interprets information in pattern-like images rather than numerical quantities. The proposed clustering algorithm, Fuzzy Unsupervised Active Learning Method (FUALM), is performed in two main phases. First, each data point spreads in the feature space just like an ink drop that spreads on a sheet of paper. As a result of this process, densely connected ink patterns are formed that represent clusters. In the second phase, a fuzzifying process is applied in order to summarize the effects... 

This study introduces a new identifier for nuclear power plants (NPPs) transients. The proposed identifier performs its function in two steps. First, the transient is identified by the previously developed supervised classifier combining ARIMA model and EBP algorithm. In the second step, the patterns of unknown transients are fed to the identifier based on the semi-supervised learning (SSL). The transductive support vector machine (TSVM) as a semi-supervised algorithm is trained by the labeled data of transients to predict some unlabeled data. The labeled and newly predicted data is then used to train the TSVM for another portion of unlabeled data. Training and prediction is continued until... 

In this paper, we propose a novel density-based fuzzy clustering algorithm based on Active Learning Method (ALM), which is a methodology of soft computing inspired by some hypotheses claiming that human brain interprets information in pattern-like images rather than numerical quantities. The proposed clustering algorithm, Fuzzy Unsupervised Active Learning Method (FUALM), is performed in two main phases. First, each data point spreads in the feature space just like an ink drop that spreads on a sheet of paper. As a result of this process, densely connected ink patterns are formed that represent clusters. In the second phase, a fuzzifying process is applied in order to summarize the effects... 

Online social networks play a major role in modern societies, and they have shaped the way social relationships evolve. Link prediction in social networks has many potential applications such as recommending new items to users, friendship suggestion and discovering spurious connections. Many real social networks evolve the connections in multiple layers (e.g. multiple social networking platforms). In this article, we study the link prediction problem in multiplex networks. As an example, we consider a multiplex network of Twitter (as a microblogging service) and Foursquare (as a location-based social network). We consider social networks of the same users in these two platforms and develop a... 

In this paper we try to alleviate the problem of scares resources for developing Farsi-English Statistical Machine Translation system (SMT). It is done by applying Active Learning (AL) idea to choose more informative sentences to be translated by a human and then be added to the base-line corpus. While using the human translations is worthless in compare to the other approaches of corpus gathering (like automatic approaches), it is more costly too. So, in this way we can improve the translation system with less cost. This is done in intricate to human translator. Applying Active learning idea to a SMT system, changes it to a system which can improve its based-line corpus by asking for the... 

Hierarchical reinforcement learning facilitates learning in large and complex domains by exploiting subtasks and creating hierarchical structures using these subtasks. Subtasks are usually defined through finding subgoals of the problem. Providing mechanisms for autonomous subgoal discovery and skill acquisition is a challenging issue in reinforcement learning. Among the proposed algorithms, a few of them are successful both in performance and also efficiency in terms of the running time of the algorithm. In this paper, we study four methods for subgoal discovery which are based on graph partitioning. The idea behind the methods proposed in this paper is that if we partition the transition... 

Considering each of the visual features as one modality in image annotation task, efficient fusion of different modalities is essential in graph-based learning. Traditional graph-based methods consider one node for each image and combine its visual features into a single descriptor before constructing the graph. In this paper, we propose an approach that constructs a subgraph for each modality in such a way that edges of subgraph are determined using a search-based approach that handles class-imbalance challenge in the annotation datasets. Multiple subgraphs are then connected to each other to have a supergraph. This follows by introducing a learning framework to infer the tags of... 

While visual target tracking is one of the noteworthy and the most active research areas in computer vision and machine learning, many challenges are still unresolved. In this paper, an adaptive generic target tracker is proposed that includes the adaptive determination of learning parameters from spatio-temporal context model, analysis of prior targets and confidence map for accurate target localization, and modified scale estimation scheme based on confidence map. According to spatio-temporal context model, the learning parameters are adaptively determined for achieving confidence map and target scale robustly. Moreover, analysis of the confidence map helps our tracker to change context... 

Purpose: Different studies have analyzed the relationship between organizational learning (OL) and innovation performance (IP). However, the question of how innovation culture (IC) affects the relationship between OL and IP remains unexplored. This study aims to examine the impact of IC on the relationship between OL and various dimensions of IP, including product, process and objective innovation. Design/methodology/approach: A research model was developed and performed based on the relevant literature in the field of OL, IC and IP. The hypotheses are tested with the data collected from companies operating in an intensive knowledge-based industry. Findings: Based on the results of 625... 

The efficiency of a learning process directly depends on how well the students are attentive. Detecting the level of attention can help to improve the learning quality. In recent years, there have been several attempts to leverage EEG signal processing as a tool to detect whether a student is attentive or not. In such work, the level of attention is determined by analyzing the EEG power spectrum, which is mostly followed by machine learning approaches. However, the efficiency of such methods for detecting auditory attention of blind or visually-impaired students has not been analyzed. This study aims to investigate such a scenario. To this end, we propose an EEG recording protocol to... 

Entanglement is one of the key resources of quantum information science which makes identification of entangled states essential to a wide range of quantum technologies and phenomena. This problem is however both computationally and experimentally challenging. Here we use autoencoder neural networks to find semi-optimal set of incomplete measurements that are most informative for the detection of entangled states. We show that it is possible to find high-performance entanglement detectors with as few as three measurements. Also, with the complete information of the state, we develop a neural network that can identify all two-qubits entangled states almost perfectly. This result paves the way... 

Market prediction has been an important research problem for decades. Having better predictive models that are both more accurate and faster has been attractive for both researchers and traders. Among many approaches, semi-supervised graph-based prediction has been used as a solution in recent researches. Based on this approach, we present two prediction models. In the first model, a new network structure is introduced that can capture more information about markets’ direction of movements compared to the previous state of the art methods. Based on this novel network, a new algorithm for semi-supervised label propagation is designed that is able to prediction the direction of movement faster... 

Internet-of-Things (IoT) devices and applications are being deployed in our homes and workplaces. These devices often rely on continuous data collection to feed machine learning models. However, this approach introduces several privacy and efficiency challenges, as the service operator can perform unwanted inferences on the available data. Recently, advances in edge processing have paved the way for more efficient, and private, data processing at the source for simple tasks and lighter models, though they remain a challenge for larger and more complicated models. In this article, we present a hybrid approach for breaking down large, complex deep neural networks for cooperative, and...