Idea Of Learning Research Articles

Dual Mutual Information Constraints for Discriminative Clustering

Deep clustering is a fundamental task in machine learning and data mining that aims at learning clustering-oriented feature representations. In previous studies, most of deep clustering methods follow the idea of self-supervised representation learning by maximizing the consistency of all similar instance pairs while ignoring the effect of feature redundancy on clustering performance. In this paper, to address the above issue, we design a dual mutual information constrained clustering method named DMICC which is based on deep contrastive clustering architecture, in which the dual mutual information constraints are particularly employed with solid theoretical guarantees and experimental validations. Specifically, at the feature level, we reduce the redundancy among features by minimizing the mutual information across all the dimensionalities to encourage the neural network to extract more discriminative features. At the instance level, we maximize the mutual information of the similar instance pairs to obtain more unbiased and robust representations. The dual mutual information constraints happen simultaneously and thus complement each other to jointly optimize better features that are suitable for the clustering task. We also prove that our adopted mutual information constraints are superior in feature extraction, and the proposed dual mutual information constraints are clearly bounded and thus solvable. Extensive experiments on five benchmark datasets show that our proposed approach outperforms most other clustering algorithms. The code is available at https://github.com/Li-Hyn/DMICC.

Doodle to Object: Practical Zero-Shot Sketch-Based 3D Shape Retrieval

Zero-shot (ZS) sketch-based three-dimensional (3D) shape retrieval (SBSR) is challenging due to the abstraction of sketches, cross-domain discrepancies between two-dimensional sketches and 3D shapes, and ZS-driven semantic knowledge transference from seen to unseen categories. Extant SBSR datasets suffer from lack of data, and no current SBSR methods consider ZS scenarios. In this paper, we contribute a new Doodle2Object (D2O) dataset consisting of 8,992 3D shapes and over 7M sketches spanning 50 categories. Then, we propose a novel prototype contrastive learning (PCL) method that effectively extracts features from different domains and adapts them to unseen categories. Specifically, our PCL method combines the ideas of contrastive and cluster-based prototype learning, and several randomly selected prototypes of different classes are assigned to each sample. By comparing these prototypes, a given sample can be moved closer to the same semantic class of samples while moving away from negative ones. Extensive experiments on two common SBSR benchmarks and our D2O dataset demonstrate the efficacy of the proposed PCL method for ZS-SBSR. Resource is available at https://github.com/yigohw/doodle2object.

Provable Pathways: Learning Multiple Tasks over Multiple Paths

Constructing useful representations across a large number of tasks is a key requirement for sample-efficient intelligent systems. A traditional idea in multitask learning (MTL) is building a shared representation across tasks which can then be adapted to new tasks by tuning last layers. A desirable refinement of using a shared one-fits-all representation is to construct task-specific representations. To this end, recent PathNet/muNet architectures represent individual tasks as pathways within a larger supernet. The subnetworks induced by pathways can be viewed as task-specific representations that are composition of modules within supernet's computation graph. This work explores the pathways proposal from the lens of statistical learning: We first develop novel generalization bounds for empirical risk minimization problems learning multiple tasks over multiple paths (Multipath MTL). In conjunction, we formalize the benefits of resulting multipath representation when adapting to new downstream tasks. Our bounds are expressed in terms of Gaussian complexity, lead to tangible guarantees for the class of linear representations, and provide novel insights into the quality and benefits of a multipath representation. When computation graph is a tree, Multipath MTL hierarchically clusters the tasks and builds cluster-specific representations. We provide further discussion and experiments for hierarchical MTL and rigorously identify the conditions under which Multipath MTL is provably superior to traditional MTL approaches with shallow supernets.

Self-Supervised Primal-Dual Learning for Constrained Optimization

This paper studies how to train machine-learning models that directly approximate the optimal solutions of constrained optimization problems. This is an empirical risk minimization under constraints, which is challenging as training must balance optimality and feasibility conditions. Supervised learning methods often approach this challenge by training the model on a large collection of pre-solved instances. This paper takes a different route and proposes the idea of Primal-Dual Learning (PDL), a self-supervised training method that does not require a set of pre-solved instances or an optimization solver for training and inference. Instead, PDL mimics the trajectory of an Augmented Lagrangian Method (ALM) and jointly trains primal and dual neural networks. Being a primal-dual method, PDL uses instance-specific penalties of the constraint terms in the loss function used to train the primal network. Experiments show that, on a set of nonlinear optimization benchmarks, PDL typically exhibits negligible constraint violations and minor optimality gaps, and is remarkably close to the ALM optimization. PDL also demonstrated improved or similar performance in terms of the optimality gaps, constraint violations, and training times compared to existing approaches.

Beyond Black-Boxes: Teaching Complex Machine Learning Ideas through Scaffolded Interactive Activities

Existing approaches to teaching artificial intelligence and machine learning (ML) often focus on the use of pre-trained models or fine-tuning an existing black-box architecture. We believe ML techniques and core ML topics, such as optimization and adversarial examples, can be designed for high school age students given appropriate support. Our curricular approach focuses on teaching ML ideas by enabling students to develop deep intuition about these complex concepts by first making them accessible to novices through interactive tools, pre-programmed games, and carefully designed programming activities. Then, students are able to engage with the concepts via meaningful, hands-on experiences that span the entire ML process from data collection to model optimization and inspection. This paper describes our 'AI & Cybersecurity for Teens' suite of curricular activities aimed at high school students and teachers.

The Impact of Behaviorist Theories and the Legal System Laws Developed from Them

The theories, which stress how environmental cues act as catalysts for criminal action, are based on ideas of imitation and learning. To comprehend criminal behavior as a learned or copied reaction to societal and environmental stimuli, this research emphasizes the significance of psychological deviations. The macro and micro layers of crimes are the main topics of this study’s investigation of psychological theories of the criminal justice system. In order to understand how societal and environmental factors affect individual criminal conduct, sociological and psychological perspectives on crime are used in this analysis. The idea of a mentor or guide is introduced, making the argument that people frequently need assistance and direction to develop their personalities. This research concludes that in the 20th century, blatant crimes such as drug trafficking and gambling undermined the rights of others to life and permanently severed the person from the mental conscious level, transferring him to an unconscious, unreal, obscured, and incomprehensible reality. This article reveals that men struggle more than women to communicate and comprehend their emotions, which makes them more likely to be charged with crimes.

Exploring the potential of Siamese network for RGBT object tracking

Siamese tracking is one of the most promising object tracking methods today due to its balance of performance and speed. However, it still performs poorly when faced with some challenges such as low light or extreme weather. This is caused by the inherent limitations of visible images, and a common way to cope with it is to introduce infrared data as an aid to improve the robustness of tracking. However, most of the existing RGBT trackers are variants of MDNet (Hyeonseob Nam and Bohyung Han, Learning multi-domain convolutional neural networks for visual tracking, in: Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 4293–4302.), which have significant limitations in terms of operational efficiency. On the contrary, the potential of Siamese tracking in the field of RGBT tracking has not been effectively exploited due to the reliance on large-scale training data. To solve this dilemma, in this paper, we propose an end-to-end Siamese RGBT tracking framework that is based on cross-modal feature enhancement and self-attention (SiamFEA). We draw on the idea of migration learning and employ local fine-tuning to reduce the dependence on large-scale RGBT data and verify the feasibility of this approach, and then we propose a reliable fusion approach to efficiently fuse the features of different modalities. Specifically, we first propose a cross-modal feature enhancement module to exploit the complementary properties of dual-modality, followed by capturing non-local attention in channel and spatial dimensions for adaptive weighted fusion, respectively. Our network was trained end-to-end on the LasHeR (Chenglong Li, Wanlin Xue, Yaqing Jia, Zhichen Qu, Bin Luo, Jin Tang, LasHeR: A Large-scale High-diversity Benchmark for RGBT Tracking, CoRR abs/2104.13202, 2021) training set and reached new SOTAs on GTOT (C. Li, H. Cheng, S. Hu, X. Liu, J. Tang, L. Lin, Learning collaborative sparse representation for grayscale-thermal tracking, IEEE Trans. Image Process, 25 (12) (2016) 5743–5756.), RGBT234 (C. Li, X. Liang, Y. Lu, N. Zhao, and J. Tang, “Rgb-t object tracking: Benchmark and baseline,” Pattern Recognition, vol. 96, p. 106977, 2019.), and LasHeR (Chenglong Li, Wanlin Xue, Yaqing Jia, Zhichen Qu, Bin Luo, Jin Tang, LasHeR: A Large-scale High-diversity Benchmark for RGBT Tracking, CoRR abs/2104.13202, 2021) while running in real-time.

Gas-expensive patterns detection to optimize smart contracts

Smart contracts are programmable protocols that run on Ethereum and require gas to be deployed and used. Gas-expensive operations in some smart contracts can cause users to consume extra gas in transactions. There are already several methods to detect gas-expensive patterns in smart contracts. However, some problems still need to be solved: most static analysis methods are based on specialist knowledge, and the patterns used to detect gas-expensive patterns must be manually summarized before the detection methods can be applied. Furthermore, due to the explosive growth of smart contracts, which generate a large amount of data, it is challenging to reuse these methods across different patterns. To address these issues, this work first proposes a new learning-based method, ExpenGas, based on the idea of evolutionary computation-based machine learning to detect Expensive Operation patterns of smart contracts through pre-trained techniques and multi-crucial data flow graphs. The low complexity of the multi-crucial data flow graph enables the model to focus on key features. Finally, by testing on 21981 smart contract files, ExpenGas has 83.05% accuracy and 91.96% recall in detecting the Expensive Operation patterns of gas-expensive patterns, which is significantly more optimal than the current state-of-the-art methods.

Paradigms of Relationships in Faulkner, Woolf and Vian

The paradigms within human relationship are shaped by a multitude of factors which tug at the edges of the ability to form interpersonal bonds with the influence of experience. What constitutes experience, then, can be argued in several different manners. However, it is the interpretation of conventional, institutional education in the minds of the characters in Williams Faulkner’s Light in August, Virginia Woolf’s To the Lighthouse, and Boris Vian’s Mood Indigo that sets a course for the trajectory of their relationships with others and with themselves. The various frameworks of the characters’ respective educations allow them to express what has been fed to them and how to interpret, knowledge. Once they are able to identify what constitutes experience through learning, these concepts, religious tenets, the awareness of factual circumstances, fixed categories imposed on reality, and ostensible truth as defined by ideology, are applied to models of human relationship, often with disastrous or emotionally numbing results through sticking to a pre-defined notion of how to apply what one is taught to one’s personal life. The characters of Light in August utilize an organic absorption of conventional education and religion as a form of teaching, as well as relying on past experience and intuition to traverse through their relationships, while the intellectual pursuits of the Ramsays and their acquaintances (particularly the male figures) in To the Lighthouse lead them to define relationship using ideas instead of raw emotion and experience. In comparison, the beautiful and tragic youth of Mood Indigo transform conventional education into goods for material consumption, as notions of the intellectual become synonymous with an indulgence in objectifying traditional forms of knowledge in monetary, and even human, form. The point at which education and desires converge and possibly become inseparable, then, marks the intersection not only between the compromise of relationships co-existing with powerful, learned ideas, but also the parallels between how self-acquired education through experience can differ from institutionalized thought. Can the distinctions between these methods lead to more or less successful relationships, or do they arrive at the same conclusion; the disintegration of previously cherished relationships? Is it then possible for education and relationship to co-exist peacefully? If not, perhaps it is this collision in the world of fiction that catalyzes the characters’ perpetual uncertainty with regard to both ideas.

Adaptive transfer learning for PINN

Physics-informed neural networks (PINNs) have shown great potential in solving computational physics problems with sparse, noisy, unstructured, and multi-fidelity data. However, the training of PINN remains a challenge, and PINN is not robust to deal with some complex problems, such as the sharp local gradient in broad computational domains, etc. Transfer learning techniques can provide fast and accurate training for PINN through intelligent initialization, but the previous researches are much less effective when dealing with transfer learning cases with a large range of parameter variation, which also suffers from the same drawbacks. This manuscript develops the concept of the minimum energy path for PINN and proposes an adaptive transfer learning for PINN (AtPINN). The Partial Differential Equations (PDEs) parameters are initialized by the source parameters and updated adaptively to the target parameters during the training process, which can guide the optimization of PINN from the source to the target task. This process is essentially performed along a designed low-loss path, which is no barrier in the energy landscape of neural networks. Consequently, the stability of the training process is guaranteed. AtPINN is utilized to achieve transfer learning cases with a large range of parameter variation for solving five complex problems. The results demonstrate that AtPINN has promising potential for extending the application of PINN. Besides, three transfer learning cases with different ranges of parameter variation are analyzed through visualization. Furthermore, results also show that the idea of adaptive transfer learning can be a particular optimization strategy to directly solve problems without intelligent initialization.

Mask recognition in computer vision technology

In order to lessen the strain on employees and the potential for carelessness, intelligent identification is required in China where there is a scarcity of staff to monitor the wearing of masks in public areas. In this work, we use a mask recognition technique to determine which members of the population weren't wearing masks by using the CNN and the VGG16 model. The ideas of data augmentation, dropout, non malicious, and transfer learning are used in the proposed study. This method may be used at hospitals, retail centers, transit hubs, dining establishments, and other community gatherings that require monitoring.

MUSICAL INSTRUMENTS AND NATIVE LANGUAGE LEARNING AMONG RUNGUS IN SABAH, MALAYSIA

Native Language learning is a complex and remarkable achievement because the process generally emerges from unique interactions that distributed across social networks and is embodied in individuals. Accordingly, scholars portray the need of a specific approach in native language learning. Among the native learning approach identified is the ‘experiential learning’, an approach based on the idea of learning from experience as the path to lifelong learning and development. Scholars who is a fan of the learning approach argues that providing the learners an opportunity to learn through experience thus become immensely valuable. Some even specifically suggest that musical instruments can be used as a promising experience based instructional instrument in language learning. But how exactly the musical instruments affect native language learning process? Through the application of a mixed-method approach, this paper examines the relationship between musical instruments and the native language learning via the lens of Rungus in Sabah, Malaysia. It shows that the musical instruments affect the native language learning among Rungus in Sabah, Malaysia. What this now hinted is that the musical instruments are an important part of a successful native language learning process, thus made it clear the need among instructors to consider musical instruments as part of their teaching activities.

FedCL: Federated contrastive learning for multi-center medical image classification

Federated learning, which allows distributed medical institutions to train a shared deep learning model with privacy protection, has become increasingly popular recently. However, in practical application, due to data heterogeneity between different hospitals, the performance of the model will be degraded in the training process. In this paper, we propose a federated contrastive learning (FedCL) approach. FedCL integrates the idea of contrastive learning into the federated learning framework. Specifically, it combines the local model and the global model for contrastive learning, so that the local model gradually approaches the global model with the increase of communication rounds, which improves the generalization ability of the model. We validate our method on two public datasets. Extensive experiments show that our method is superior to other federated learning algorithms in medical image classification.

Approximate Optimal Control for Nonlinear Systems With Periodic Event-Triggered Mechanism.

This article investigates the approximate optimal control problem for nonlinear affine systems under the periodic event triggered control (PETC) strategy. In terms of optimal control, a theoretical comparison of continuous control, traditional event-based control (ETC), and PETC from the perspective of stability convergence, concluding that PETC does not significantly affect the convergence rate than ETC. It is the first time to present PETC for optimal control target of nonlinear systems. A critic network is introduced to approximate the optimal value function based on the idea of reinforcement learning (RL). It is proven that the discrete updating time series from PETC can also be utilized to determine the updating time of the learning network. In this way, the gradient-based weight estimation for continuous systems is developed in discrete form. Then, the uniformly ultimately bounded (UUB) condition of controlled systems is analyzed to ensure the stability of the designed method. Finally, two illustrative examples are given to show the effectiveness of the method.

Retention Learning of Students in Machine Language: What can Culturo-Techno-Contextual Approach (CTCA) do?

This study aimed to determine the difference between (a) the retention of information by students taught machine learning using the culturo-techno-contextual approach (CTCA) and the lecture method; (b) the retention of information by male and female students taught machine learning using CTCA; and (c) the interaction effects of gender and the teaching methods on the retention of information by students taught machine learning using CTCA and lecture. Adopted learning ideas include Vygotsky's theory of constructivism, Ausubel's philosophy of meaningful learning, and the philosophical framework of the CTCA. This study employed sequential explanatory mixed methodologies and a quasi-experimental research methodology. A total of 138 learners in senior secondary II participated in the study. The reliability of the Machine Language Achievement Test (MLAT) was determined using the split-half method, which yielded a Spearman-Brown coefficient of 0.80. There is a statistically significant difference in method of teaching [F (1, 137) = 111.61; p<0.05], which was in favour of the CTCA group (experimental). There is no statistically significant difference in the gender of the students in the experimental group [F (1, 137) = 0.08; p > 0.05]. The interaction effect of methods and gender is not statistically significant [F (1, 137) = 1.61; p = 0.21]. We therefore encouraged and suggested that secondary school computer studies teachers should utilise CTCA in order to improve student learning.

House price prediction based on machine learning

Machine learning is commonly used in the real estate market. It is vital to apply the idea of machine learning in this field to predict house prices based on various features. The paper will focus on how to use the most appropriate machine learning models for house price prediction. It will use LightGBM(Light Gradient Boosting Machine), Gradient Boosting, and XGBoost(Extreme Gradient Boosting) to train models to predict house prices using the existing data from the Kaggle website. After three models make predictions, they will get an RMSE (root mean square error), whichis0.02975, 0.02537, and 0.01364. Based on the result, the XGBoost model is the best one among these three models used for house price prediction.

Prediction of small molecule drug-miRNA associations based on GNNs and CNNs.

MicroRNAs (miRNAs) play a crucial role in various biological processes and human diseases, and are considered as therapeutic targets for small molecules (SMs). Due to the time-consuming and expensive biological experiments required to validate SM-miRNA associations, there is an urgent need to develop new computational models to predict novel SM-miRNA associations. The rapid development of end-to-end deep learning models and the introduction of ensemble learning ideas provide us with new solutions. Based on the idea of ensemble learning, we integrate graph neural networks (GNNs) and convolutional neural networks (CNNs) to propose a miRNA and small molecule association prediction model (GCNNMMA). Firstly, we use GNNs to effectively learn the molecular structure graph data of small molecule drugs, while using CNNs to learn the sequence data of miRNAs. Secondly, since the black-box effect of deep learning models makes them difficult to analyze and interpret, we introduce attention mechanisms to address this issue. Finally, the neural attention mechanism allows the CNNs model to learn the sequence data of miRNAs to determine the weight of sub-sequences in miRNAs, and then predict the association between miRNAs and small molecule drugs. To evaluate the effectiveness of GCNNMMA, we implement two different cross-validation (CV) methods based on two different datasets. Experimental results show that the cross-validation results of GCNNMMA on both datasets are better than those of other comparison models. In a case study, Fluorouracil was found to be associated with five different miRNAs in the top 10 predicted associations, and published experimental literature confirmed that Fluorouracil is a metabolic inhibitor used to treat liver cancer, breast cancer, and other tumors. Therefore, GCNNMMA is an effective tool for mining the relationship between small molecule drugs and miRNAs relevant to diseases.

On the question of the establishment and development of languages education in Canada (XVII - the beginning of XXI century)

The article is devoted to the study of the theoretical and organizational foundations of language teaching in the Canadian education system in the context of globalization processes and multilingual society. The work presents a retrospective analysis of the formation and development of language teaching in the Canadian education system from the beginning of organized education to the beginning of the 21st century, highlights certain issues of state regulation in the field of language education in Canada. The socio-political context of the development of multilingualism in Canada is analyzed and the stages of formation and development of a multilingual society are determined.The work reveals the peculiarities of the organization of L1, L2 and FL learning at various levels of the Canadian education system. The conceptual ideas of language learning in Canadian pedagogical research are defined; the specifics of language training of citizens in the Canadian education system, taking into account the bilingual nature of society, are identified; the newest methods and trends in development of language education in Canada are reviewed.On the basis of a comparison of the language training practice in Ukraine and Canada, certain elements of the positive Canadian experience have been identified, which are expedient to use in the national education system in the conditions of the creation of the European context of language education.

Student expectations of teaching and learning when starting university: a systematic review

ABSTRACT Student expectations are complex constructs that can influence adaptability, engagement, achievement, satisfaction and retention. A number of individual studies have been published on the expectations of students when starting university, however none that synthesise student expectations of teaching and learning. Therefore, the aim of this systematic review was to understand student expectations of teaching and learning when starting university. A systematic search strategy identified 2950 studies, of which nine met all eligibility criteria. Relevant data was extracted and a narrative synthesis conducted, revealing four key themes: additional study, self-managing learning, teaching and learning activities, and accessibility. Students expect to complete additional study and take responsibility for their own learning, but may be unsure how to manage this. They expect to have to attend all sessions and commonly expect lectures, but thoughts on other methods of teaching and learning vary. Students also have high expectations of teaching staff, particularly with regards to access and resources. This knowledge is important in enabling teaching staff to better align preconceived ideas of university teaching and learning with reality, support a positive university experience, and improve satisfaction and retention. Future research should further investigate student expectations of teaching and learning independently, perhaps from a qualitative perspective, as well as exploring interventions to help manage these expectations when necessary.

A Fast Data-Driven Iteratively Regularized Method with Convex Penalty for Solving Ill-Posed Problems

We propose a new iterative regularization method for solving inverse problems in Hilbert spaces. The iterative process of the proposed method combines classical iterative regularization format and Data-Driven approach. Data-Driven technique is based on the idea of deep learning to estimate the interior of a black box through a training set, so as to solve problems better and faster in some cases. In order to capture the special feature of solutions, convex functions are utilized to be penalty terms. Algorithmically, the two-point gradient acceleration strategy based on homotopy perturbation method is applied to the iterative scheme, which makes the method have satisfactory acceleration effect. We provide convergence analysis of the method under standard assumptions for iterative regularization methods. Finally, several numerical experiments are presented to show the effectiveness and acceleration effect of our method.