Journal articles: 'Broad Structural Representation Learning'

1

Worden, Keith, and Graeme Manson. "The application of machine learning to structural health monitoring." Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences 365, no. 1851 (December 12, 2006): 515–37. http://dx.doi.org/10.1098/rsta.2006.1938.

Full text

Abstract:

In broad terms, there are two approaches to damage identification. Model-driven methods establish a high-fidelity physical model of the structure, usually by finite element analysis, and then establish a comparison metric between the model and the measured data from the real structure. If the model is for a system or structure in normal (i.e. undamaged) condition, any departures indicate that the structure has deviated from normal condition and damage is inferred. Data-driven approaches also establish a model, but this is usually a statistical representation of the system, e.g. a probability density function of the normal condition. Departures from normality are then signalled by measured data appearing in regions of very low density. The algorithms that have been developed over the years for data-driven approaches are mainly drawn from the discipline of pattern recognition, or more broadly, machine learning. The object of this paper is to illustrate the utility of the data-driven approach to damage identification by means of a number of case studies.

APA, Harvard, Vancouver, ISO, and other styles

2

Arney, Noah D., and Hilary P. Krygsman. "Work-Integrated Learning Policy in Alberta: A Post-Structural Analysis." Canadian Journal of Educational Administration and Policy, no. 198 (February 17, 2022): 97–110. http://dx.doi.org/10.7202/1086429ar.

Full text

Abstract:

In late 2020 the Government of Alberta’s Ministry of Advanced Education sent a guidance document to Alberta post-secondary institutions to lay out how work-integrated learning was to be conducted. This document also informed the institutions that work-integrated learning should be included in all future program proposals. The guidelines were sent without the context or purpose stated. This paper applies Carol Bacchi’s “What’s the Problem Represented to be” post-structural policy discourse analysis to the Ministry of Advanced Education guidelines. There is a broad consensus in work-integrated learning research that work-integrated learning is beneficial for participants beyond employment outcomes. However, this analysis shows the Ministry of Advanced Education’s representation of the problem displays an assumption that the purpose of work-integrated learning is to improve labour market outcomes. The analysis also spotlights that the likely effects of the policy have more to do with making work-integrated learning programs easier to assess than to improve student education. This paper proposes an alternative framework that would integrate the constructivist and humanistic origin of work-integrated learning and allow institutions to develop appropriate experiential learning components for their programs while still standardizing work-integrated learning components across and within institutions. This proposed framework can improve work-integrated learning programs in Canada by widening the focus beyond human capital theory.

APA, Harvard, Vancouver, ISO, and other styles

3

Quintana, Rafael. "The ecology of human behavior: A network perspective." Methodological Innovations 15, no. 1 (March 2022): 42–61. http://dx.doi.org/10.1177/20597991221077911.

Full text

Abstract:

There is a broad agreement that some of the most relevant problems in the social and behavioral sciences are fundamentally structural, and as a consequence require structural explanations. Yet researchers disagree on what a structural explanation is, and what are the specific questions that can only be answered through a structural lens. In this study, I shed some light on the nature of structural explanations by distinguishing between three types of structural questions related to structural proximity, structural cohesion and structural importance. In addition, I show how graphical methods can be used to answer these questions. In particular, I argue that structure learning algorithms can help us gain some understanding regarding causal structures, and network science can help us understand the organization of these structures. I provide an empirical application of these methods using a nationally representative dataset with a wide range of factors related to child development.

APA, Harvard, Vancouver, ISO, and other styles

4

Bingman, Verner P., and Rubén N. Muzio. "Reflections on the Structural-Functional Evolution of the Hippocampus: What Is the Big Deal about a Dentate Gyrus." Brain, Behavior and Evolution 90, no. 1 (2017): 53–61. http://dx.doi.org/10.1159/000475592.

Full text

Abstract:

The vertebrate hippocampal formation has been central in discussions of comparative cognition, nurturing an interest in understanding the evolution of variation in hippocampal organization among vertebrate taxa and the functional consequences of that variation. Assuming some similarity between the medial pallium of extant amphibians and the hippocampus of stem tetrapods, we propose the hypothesis that the hippocampus of modern amniotes began with a medial pallium characterized by a relatively undifferentiated cytoarchitecture, more direct thalamic and olfactory sensory inputs, and a broad role in associative learning and memory processes that nonetheless included the map-like representation of space. From this modest beginning evolved the cognitively more specialized hippocampal formation of birds and the hippocampus of mammals with its confounding dentate gyrus. Much has been made of trying to identify a dentate homologue in birds, but there are compelling reasons to believe no such structural homologue/functional equivalent exists. The uniqueness of the mammalian dentate then raises the question of what might be the functional consequences of a hippocampus with a dentate compared to one without. One might be tempted to speculate that the presence of a dentate gyrus facilitates so-called pattern separation, but birds with their suspected dentate-less hippocampus display excellent hippocampal-dependent pattern separation relying on space. Perhaps one consequence of a dentate is a hippocampus better designed to process a broader array of stimuli beyond space to more robustly support episodic memory. What is clear is that any meaningful reconstruction of hippocampal evolution and the eventual identification of any subdivisional homologies will require more data on the neurobiological and functional properties of the nonmammalian hippocampus, particularly those of amphibians and reptiles.

APA, Harvard, Vancouver, ISO, and other styles

5

Singh, Ajay, Harman Preet Singh, Fakhre Alam, and Vikas Agrawal. "Role of Education, Training, and E-Learning in Sustainable Employment Generation and Social Empowerment in Saudi Arabia." Sustainability 14, no. 14 (July 19, 2022): 8822. http://dx.doi.org/10.3390/su14148822.

Full text

Abstract:

This study analyzes the role of education, training, and e-learning (ETL) in empowering Saudi society, leading to sustainable employment generation in Saudi Arabia. It applies the theory of constructivism, scoping to human aspects of teaching and learning in sustainable employment generation and social empowerment. The study primarily collects the existing variable pools from the available literature on education (EDU), training (TRA), e-learning (ELRN), government policies (GPOL), national culture (NCUL), sustainable employment generation (SUEG), and social empowerment (SEMP). The study performs second-order partial least squares structural equation modeling (PLS-SEM) with moderation analysis. The study aims to obtain the combined effect of ETL on SUEG and SEMP in the presence of GPOL and NCUL in Saudi Arabia. Primarily, the results of the path diagram show that ETL has a significant direct impact on SEMP and SUEG. Secondly, the moderation analysis results show that GPOL has been a significant moderator between ETL and SUEG and ETL and SEMP. In contrast, the analysis results show that the NCUL is not a significant moderator between ETL and SUEG, or between ETL and SEMP. Additionally, the moderation analysis results show that NCUL directly impacts SEMP. In contrast, it does not show a significant direct relationship with SUEG. In the article, the theory of constructivism emphasizes the learners’ active role in constructing knowledge, which is significant for both individuals and society, and the validity of constructed knowledge and its realistic representation in the real world. The practical implementation of the education and e-learning approach of constructivism will help to bridge the gap between the skilled workforce in Saudi Arabia and the rest of the world. Moreover, the students, as learners, will be able to assert their experiences by connecting with the outside world, constructing a sustainable society, leading to sustainable employment generation and social empowerment in Saudi Arabia. The study also has a broad scope for higher educational institutions, training centers, and organizations in Saudi Arabia and the rest of the world.

APA, Harvard, Vancouver, ISO, and other styles

6

McConaghy, Cathryn. "on Pedagogy, Trauma and Difficult Memory: Remembering Namatjira, our Beloved." Australian Journal of Indigenous Education 32 (2003): 11–20. http://dx.doi.org/10.1017/s1326011100003781.

Full text

Abstract:

AbstractOne of the projects engaged in within the text Rethinking Indigenous Education (RIE) (McConaghy, 2000) was an analysis of the colonial regimes that are reproduced within Indigenous education, often despite our emancipatory intentions. Through a detailed critique of the various competitions for epistemic authority in the field, the book explores the structural processes by which certain knowledges are legitimated as “truths” and the material and symbolic effects of these.The focus of the book was on the imagined worlds of various traditions of knowing Indigenous education and their claims to authority. It was a “how” rather than a “who” story that dealt with theoretical assumptions, broad-brush policy and curriculum inquiry and that attempted to avoid the identity politics that had gripped Indigenous education for more than a decade. Importantly the book also suggested that rather than being cumulative, critique is a process that needs to be ongoing, done again and again. This paper, Remembering Namatjira, has sought to move beyond the main projects of RIE, many of them structural in nature, to an analysis of more intimate aspects of Indigenous education. It addresses some of the “who” issues, not in terms of representation politics, who can know and speak what, but in terms of the psychic difficulties that we attach to knowledge in Indigenous education. Whereas RIE drew upon postcolonial and feminist insights, this paper considers the contribution of psychoanalysis to thinking through some of the more intractable issues that remain unexamined or underexamined in the field. Among the issues addressed are the fundamental dilemmas around our ambivalences in education; the notion of pedagogical force (and transferences, resistances and obstacles to learning); the work of ethical witnessing; and issues of difficult knowledge, or knowledge and memories that we cannot bear to know. Central to the work of rethinking Indigenous education again, in moving beyond deconstruction, is the process of making meaning out of the ruins of our lovely knowledges (Britzman, 2003), our comfort knowledges, about what should be done in Indigenous education.

APA, Harvard, Vancouver, ISO, and other styles

7

Orynbaikyzy, Aiym, Ursula Gessner, Benjamin Mack, and Christopher Conrad. "Crop Type Classification Using Fusion of Sentinel-1 and Sentinel-2 Data: Assessing the Impact of Feature Selection, Optical Data Availability, and Parcel Sizes on the Accuracies." Remote Sensing 12, no. 17 (August 27, 2020): 2779. http://dx.doi.org/10.3390/rs12172779.

Full text

Abstract:

Crop type classification using Earth Observation (EO) data is challenging, particularly for crop types with similar phenological growth stages. In this regard, the synergy of optical and Synthetic-Aperture Radar (SAR) data enables a broad representation of biophysical and structural information on target objects, enhancing crop type mapping. However, the fusion of multi-sensor dense time-series data often comes with the challenge of high dimensional feature space. In this study, we (1) evaluate how the usage of only optical, only SAR, and their fusion affect the classification accuracy; (2) identify the combination of which time-steps and feature-sets lead to peak accuracy; (3) analyze misclassifications based on the parcel size, optical data availability, and crops’ temporal profiles. Two fusion approaches were considered and compared in this study: feature stacking and decision fusion. To distinguish the most relevant feature subsets time- and variable-wise, grouped forward feature selection (gFFS) was used. gFFS allows focusing analysis and interpretation on feature sets of interest like spectral bands, vegetation indices (VIs), or data sensing time rather than on single features. This feature selection strategy leads to better interpretability of results while substantially reducing computational expenses. The results showed that, in contrast to most other studies, SAR datasets outperform optical datasets. Similar to most other studies, the optical-SAR combination outperformed single sensor predictions. No significant difference was recorded between feature stacking and decision fusion. Random Forest (RF) appears to be robust to high feature space dimensionality. The feature selection did not improve the accuracies even for the optical-SAR feature stack with 320 features. Nevertheless, the combination of RF feature importance and time- and variable-wise gFFS rankings in one visualization enhances interpretability and understanding of the features’ relevance for specific classification tasks. For example, by enabling the identification of features that have high RF feature importance values but are, in their information content, correlated with other features. This study contributes to the growing domain of interpretable machine learning.

APA, Harvard, Vancouver, ISO, and other styles

8

Fasoulis, Romanos, Georgios Paliouras, and Lydia E. Kavraki. "Graph representation learning for structural proteomics." Emerging Topics in Life Sciences 5, no. 6 (October 19, 2021): 789–802. http://dx.doi.org/10.1042/etls20210225.

Full text

Abstract:

The field of structural proteomics, which is focused on studying the structure–function relationship of proteins and protein complexes, is experiencing rapid growth. Since the early 2000s, structural databases such as the Protein Data Bank are storing increasing amounts of protein structural data, in addition to modeled structures becoming increasingly available. This, combined with the recent advances in graph-based machine-learning models, enables the use of protein structural data in predictive models, with the goal of creating tools that will advance our understanding of protein function. Similar to using graph learning tools to molecular graphs, which currently undergo rapid development, there is also an increasing trend in using graph learning approaches on protein structures. In this short review paper, we survey studies that use graph learning techniques on proteins, and examine their successes and shortcomings, while also discussing future directions.

APA, Harvard, Vancouver, ISO, and other styles

9

Li, Cheng-Te, and Hong-Yu Lin. "Structural Hierarchy-Enhanced Network Representation Learning." Applied Sciences 10, no. 20 (October 16, 2020): 7214. http://dx.doi.org/10.3390/app10207214.

Full text

Abstract:

Network representation learning (NRL) is crucial in generating effective node features for downstream tasks, such as node classification (NC) and link prediction (LP). However, existing NRL methods neither properly identify neighbor nodes that should be pushed together and away in the embedding space, nor model coarse-grained community knowledge hidden behind the network topology. In this paper, we propose a novel NRL framework, Structural Hierarchy Enhancement (SHE), to deal with such two issues. The main idea is to construct a structural hierarchy from the network based on community detection, and to utilize such a hierarchy to perform level-wise NRL. In addition, lower-level node embeddings are passed to higher-level ones so that community knowledge can be aware of in NRL. Experiments conducted on benchmark network datasets show that SHE can significantly boost the performance of NRL in both tasks of NC and LP, compared to other hierarchical NRL methods.

APA, Harvard, Vancouver, ISO, and other styles

10

Romero, Lisa S. "Trust, behavior, and high school outcomes." Journal of Educational Administration 53, no. 2 (April 13, 2015): 215–36. http://dx.doi.org/10.1108/jea-07-2013-0079.

Full text

Abstract:

Purpose – The purpose of this paper is to contribute to the literature on student trust and to examine the relationship between student trust, behavior, and academic outcomes in high school. It asks, first, does trust have a positive effect on high school outcomes? Second, does trust influence student behavior, exerting an indirect effect on schooling outcomes? Third, are school size and student socioeconomic status (SES) antecedents of trust? Design/methodology/approach – A nationally representative sample of students attending public high schools in the USA (n=10,585) is drawn from the Educational Longitudinal Study. Structural equation modeling is used to examine the relationship between student trust, behavior and high school outcomes, controlling for SES, school size and prior achievement. Multiple measures of academic achievement are considered. Findings – There is a significant relationship between student trust, behavior and high school outcomes. Students who trust have fewer behavioral incidents and better academic outcomes with results suggesting that trust functions through behavior. This is true regardless of SES, school size or prior achievement. Practical implications – School leaders cannot change parental income or education, but can build trust. Developing and attending to student trust may not only mean that students are better behaved but, more importantly, are more successful academically. Social implications – In spite of decades of policy and legislation intended to improve schools, closing the achievement gap has proven elusive. One reason may be the relentless focus on physical artifacts of schooling, such as school organization, curriculum, testing and accountability, and a concomitant lack of attention to sociocognitive factors key to learning. Schools are social systems, and high levels of learning are unlikely to occur without a nurturing environment that includes trust. Originality/value – This research makes a valuable contribution by focussing on student trust in high schools and by illuminating the relationship between trust, behavior, and academic outcomes. Results suggest that trust impacts a broad range of high school outcomes but functions indirectly through behavior.

APA, Harvard, Vancouver, ISO, and other styles

11

NAMATAME, AKIRA, and YOSHIAKI TSUKAMOTO. "STRUCTURAL CONNECTIONIST LEARNING WITH COMPLEMENTARY CODING." International Journal of Neural Systems 03, no. 01 (January 1992): 19–30. http://dx.doi.org/10.1142/s0129065792000036.

Full text

Abstract:

We propose a new learning algorithm, structural learning with the complementary coding for concept learning problems. We introduce the new grouping measure that forms the similarity matrix over the training set and show this similarity matrix provides a sufficient condition for the linear separability of the set. Using the sufficient condition one should figure out a suitable composition of linearly separable threshold functions that classify exactly the set of labeled vectors. In the case of the nonlinear separability, the internal representation of connectionist networks, the number of the hidden units and value-space of these units, is pre-determined before learning based on the structure of the similarity matrix. A three-layer neural network is then constructed where each linearly separable threshold function is computed by a linear-threshold unit whose weights are determined by the one-shot learning algorithm that requires a single presentation of the training set. The structural learning algorithm proceeds to capture the connection weights so as to realize the pre-determined internal representation. The pre-structured internal representation, the activation value spaces at the hidden layer, defines intermediate-concepts. The target-concept is then learned as a combination of those intermediate-concepts. The ability to create the pre-structured internal representation based on the grouping measure distinguishes the structural learning from earlier methods such as backpropagation.

APA, Harvard, Vancouver, ISO, and other styles

12

Browne, Katie, and Monica Nicolescu. "Learning to Generalize from Demonstrations." Cybernetics and Information Technologies 12, no. 3 (September 1, 2012): 27–38. http://dx.doi.org/10.2478/cait-2012-0019.

Full text

Abstract:

Abstract Learning by demonstration is a natural approach that can be used to build a robot’s task repertoire. In this paper we propose an algorithm that enables a learner to generalize a task representation from a small number of demonstrations of the same task. The algorithm can generalize a wide range of situations that typically occur in daily tasks. The paper also describes the supporting representation that we use in order to encode the generalized representation. The approach is validated with experimental results on a broad range of generalizations.

APA, Harvard, Vancouver, ISO, and other styles

13

Routh, Prahlad K., Yang Liu, Nicholas Marcella, Boris Kozinsky, and Anatoly I. Frenkel. "Latent Representation Learning for Structural Characterization of Catalysts." Journal of Physical Chemistry Letters 12, no. 8 (February 23, 2021): 2086–94. http://dx.doi.org/10.1021/acs.jpclett.0c03792.

Full text

APA, Harvard, Vancouver, ISO, and other styles

14

Feng, Qiying, Zhulin Liu, and C. L. Philip Chen. "Broad and deep neural network for high-dimensional data representation learning." Information Sciences 599 (June 2022): 127–46. http://dx.doi.org/10.1016/j.ins.2022.03.058.

Full text

APA, Harvard, Vancouver, ISO, and other styles

15

Luo, Qi, Dongxiao Yu, Akshita Maradapu Vera Venkata Sai, Zhipeng Cai, and Xiuzhen Cheng. "A survey of structural representation learning for social networks." Neurocomputing 496 (July 2022): 56–71. http://dx.doi.org/10.1016/j.neucom.2022.04.128.

Full text

APA, Harvard, Vancouver, ISO, and other styles

16

Mo, Yujie, Liang Peng, Jie Xu, Xiaoshuang Shi, and Xiaofeng Zhu. "Simple Unsupervised Graph Representation Learning." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 7 (June 28, 2022): 7797–805. http://dx.doi.org/10.1609/aaai.v36i7.20748.

Full text

Abstract:

In this paper, we propose a simple unsupervised graph representation learning method to conduct effective and efficient contrastive learning. Specifically, the proposed multiplet loss explores the complementary information between the structural information and neighbor information to enlarge the inter-class variation, as well as adds an upper bound loss to achieve the finite distance between positive embeddings and anchor embeddings for reducing the intra-class variation. As a result, both enlarging inter-class variation and reducing intra-class variation result in small generalization error, thereby obtaining an effective model. Furthermore, our method removes widely used data augmentation and discriminator from previous graph contrastive learning methods, meanwhile available to output low-dimensional embeddings, leading to an efficient model. Experimental results on various real-world datasets demonstrate the effectiveness and efficiency of our method, compared to state-of-the-art methods. The source codes are released at https://github.com/YujieMo/SUGRL.

APA, Harvard, Vancouver, ISO, and other styles

17

Jinpa, Tenzin, and Yong Gao. "Code Representation Learning Using Prüfer Sequences (Student Abstract)." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 11 (June 28, 2022): 12977–78. http://dx.doi.org/10.1609/aaai.v36i11.21625.

Full text

Abstract:

An effective and efficient encoding of the source code of a computer program is critical to the success of sequence-to-sequence deep neural network models for code representation learning. In this study, we propose to use the Prufer sequence of the Abstract Syntax Tree (AST) of a computer program to design a sequential representation scheme that preserves the structural information in an AST. Our representation makes it possible to develop deep-learning models in which signals carried by lexical tokens in the training examples can be exploited automatically and selectively based on their syntactic role and importance. Unlike other recently-proposed approaches, our representation is concise and lossless in terms of the structural information of the AST. Results from our experiment show that prufer-sequence-based representation is indeed highly effective and efficient.

APA, Harvard, Vancouver, ISO, and other styles

18

Du, Xin, Yulong Pei, Wouter Duivesteijn, and Mykola Pechenizkiy. "Fairness in Network Representation by Latent Structural Heterogeneity in Observational Data." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 04 (April 3, 2020): 3809–16. http://dx.doi.org/10.1609/aaai.v34i04.5792.

Full text

Abstract:

While recent advances in machine learning put many focuses on fairness of algorithmic decision making, topics about fairness of representation, especially fairness of network representation, are still underexplored. Network representation learning learns a function mapping nodes to low-dimensional vectors. Structural properties, e.g. communities and roles, are preserved in the latent embedding space. In this paper, we argue that latent structural heterogeneity in the observational data could bias the classical network representation model. The unknown heterogeneous distribution across subgroups raises new challenges for fairness in machine learning. Pre-defined groups with sensitive attributes cannot properly tackle the potential unfairness of network representation. We propose a method which can automatically discover subgroups which are unfairly treated by the network representation model. The fairness measure we propose can evaluate complex targets with multi-degree interactions. We conduct randomly controlled experiments on synthetic datasets and verify our methods on real-world datasets. Both quantitative and quantitative results show that our method is effective to recover the fairness of network representations. Our research draws insight on how structural heterogeneity across subgroups restricted by attributes would affect the fairness of network representation learning.

APA, Harvard, Vancouver, ISO, and other styles

19

FROMMBERGER, LUTZ. "LEARNING TO BEHAVE IN SPACE: A QUALITATIVE SPATIAL REPRESENTATION FOR ROBOT NAVIGATION WITH REINFORCEMENT LEARNING." International Journal on Artificial Intelligence Tools 17, no. 03 (June 2008): 465–82. http://dx.doi.org/10.1142/s021821300800400x.

Full text

Abstract:

The representation of the surrounding world plays an important role in robot navigation, especially when reinforcement learning is applied. This work uses a qualitative abstraction mechanism to create a representation of space consisting of the circular order of detected landmarks and the relative position of walls towards the agent's moving direction. The use of this representation does not only empower the agent to learn a certain goal-directed navigation strategy faster compared to metrical representations, but also facilitates reusing structural knowledge of the world at different locations within the same environment. Acquired policies are also applicable in scenarios with different metrics and corridor angles. Furthermore, gained structural knowledge can be separated, leading to a generally sensible navigation behavior that can be transferred to environments lacking landmark information and/or totally unknown environments.

APA, Harvard, Vancouver, ISO, and other styles

20

Joaristi, Mikel, and Edoardo Serra. "SIR-GN: A Fast Structural Iterative Representation Learning Approach For Graph Nodes." ACM Transactions on Knowledge Discovery from Data 15, no. 6 (May 19, 2021): 1–39. http://dx.doi.org/10.1145/3450315.

Full text

Abstract:

Graph representation learning methods have attracted an increasing amount of attention in recent years. These methods focus on learning a numerical representation of the nodes in a graph. Learning these representations is a powerful instrument for tasks such as graph mining, visualization, and hashing. They are of particular interest because they facilitate the direct use of standard machine learning models on graphs. Graph representation learning methods can be divided into two main categories: methods preserving the connectivity information of the nodes and methods preserving nodes’ structural information. Connectivity-based methods focus on encoding relationships between nodes, with connected nodes being closer together in the resulting latent space. While methods preserving structure generate a latent space where nodes serving a similar structural function in the network are encoded close to each other, independently of them being connected or even close to each other in the graph. While there are a lot of works that focus on preserving node connectivity, only a few works focus on preserving nodes’ structure. Properly encoding nodes’ structural information is fundamental for many real-world applications as it has been demonstrated that this information can be leveraged to successfully solve many tasks where connectivity-based methods usually fail. A typical example is the task of node classification, i.e., the assignment or prediction of a particular label for a node. Current limitations of structural representation methods are their scalability, representation meaning, and no formal proof that guaranteed the preservation of structural properties. We propose a new graph representation learning method, called Structural Iterative Representation learning approach for Graph Nodes ( SIR-GN ). In this work, we propose two variations ( SIR-GN: GMM and SIR-GN: K-Means ) and show how our best variation SIR-GN: K-Means : (1) theoretically guarantees the preservation of graph structural similarities, (2) provides a clear meaning about its representation and a way to interpret it with a specifically designed attribution procedure, and (3) is scalable and fast to compute. In addition, from our experiment, we show that SIR-GN: K-Means is often better or, in the worst-case comparable than the existing structural graph representation learning methods present in the literature. Also, we empirically show its superior scalability and computational performance when compared to other existing approaches.

APA, Harvard, Vancouver, ISO, and other styles

21

Kuok, Sin-Chi, Ka-Veng Yuen, Mark Girolami, and Stephen Roberts. "Broad learning robust semi-active structural control: A nonparametric approach." Mechanical Systems and Signal Processing 162 (January 2022): 108012. http://dx.doi.org/10.1016/j.ymssp.2021.108012.

Full text

APA, Harvard, Vancouver, ISO, and other styles

22

VAN GOMPEL, ROGER P. G., and MANABU ARAI. "Structural priming in bilinguals." Bilingualism: Language and Cognition 21, no. 3 (October 5, 2017): 448–55. http://dx.doi.org/10.1017/s1366728917000542.

Full text

Abstract:

In this review, we examine how structural priming has been used to investigate the representation of first and second language syntactic structures in bilinguals. Most experiments suggest that structures that are identical in the first and second language have a single, shared mental representation. The results from structures that are similar but not fully identical are less clear, but they may be explained by assuming that first and second language representations are merely connected rather than fully shared. Some research has also used structural priming to investigate the representation of cognate words. We will also consider whether cross-linguistic structural priming taps into long-term implicit learning effects. Finally, we discuss recent research that has investigated how second language syntactic representations develop as learners’ proficiency increases.

APA, Harvard, Vancouver, ISO, and other styles

23

Khajehnejad, Ahmad, Moein Khajehnejad, Mahmoudreza Babaei, Krishna P. Gummadi, Adrian Weller, and Baharan Mirzasoleiman. "CrossWalk: Fairness-Enhanced Node Representation Learning." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 11 (June 28, 2022): 11963–70. http://dx.doi.org/10.1609/aaai.v36i11.21454.

Full text

Abstract:

The potential for machine learning systems to amplify social inequities and unfairness is receiving increasing popular and academic attention. Much recent work has focused on developing algorithmic tools to assess and mitigate such unfairness. However, there is little work on enhancing fairness in graph algorithms. Here, we develop a simple, effective and general method, CrossWalk, that enhances fairness of various graph algorithms, including influence maximization, link prediction and node classification, applied to node embeddings. CrossWalk is applicable to any random walk based node representation learning algorithm, such as DeepWalk and Node2Vec. The key idea is to bias random walks to cross group boundaries, by upweighting edges which (1) are closer to the groups’ peripheries or (2) connect different groups in the network. CrossWalk pulls nodes that are near groups’ peripheries towards their neighbors from other groups in the embedding space, while preserving the necessary structural properties of the graph. Extensive experiments show the effectiveness of our algorithm to enhance fairness in various graph algorithms, including influence maximization, link prediction and node classification in synthetic and real networks, with only a very small decrease in performance.

APA, Harvard, Vancouver, ISO, and other styles

24

Wang, Yifei, Shiyang Chen, Guobin Chen, Ethan Shurberg, Hang Liu, and Pengyu Hong. "Motif-Based Graph Representation Learning with Application to Chemical Molecules." Informatics 10, no. 1 (January 11, 2023): 8. http://dx.doi.org/10.3390/informatics10010008.

Full text

Abstract:

This work considers the task of representation learning on the attributed relational graph (ARG). Both the nodes and edges in an ARG are associated with attributes/features allowing ARGs to encode rich structural information widely observed in real applications. Existing graph neural networks offer limited ability to capture complex interactions within local structural contexts, which hinders them from taking advantage of the expression power of ARGs. We propose motif convolution module (MCM), a new motif-based graph representation learning technique to better utilize local structural information. The ability to handle continuous edge and node features is one of MCM’s advantages over existing motif-based models. MCM builds a motif vocabulary in an unsupervised way and deploys a novel motif convolution operation to extract the local structural context of individual nodes, which is then used to learn higher level node representations via multilayer perceptron and/or message passing in graph neural networks. When compared with other graph learning approaches to classifying synthetic graphs, our approach is substantially better at capturing structural context. We also demonstrate the performance and explainability advantages of our approach by applying it to several molecular benchmarks.

APA, Harvard, Vancouver, ISO, and other styles

25

Wang, Huayan, and Qiang Yang. "Transfer Learning by Structural Analogy." Proceedings of the AAAI Conference on Artificial Intelligence 25, no. 1 (August 4, 2011): 513–18. http://dx.doi.org/10.1609/aaai.v25i1.7907.

Full text

Abstract:

Transfer learning allows knowledge to be extracted from auxiliary domains and be used to enhance learning in a target domain. For transfer learning to be successful, it is critical to find the similarity between auxiliary and target domains, even when such mappings are not obvious. In this paper, we present a novel algorithm for finding the structural similarity between two domains, to enable transfer learning at a structured knowledge level. In particular, we address the problem of how to learn a non-trivial structural similarity mapping between two different domains when they are completely different on the representation level. This problem is challenging because we cannot directly compare features across domains. Our algorithm extracts the structural features within each domain and then maps the features into the Reproducing Kernel Hilbert Space (RKHS), such that the "structural dependencies" of features across domains can be estimated by kernel matrices of the features within each domain. By treating the analogues from both domains as equivalent, we can transfer knowledge to achieve a better understanding of the domains and improved performance for learning. We validate our approach on synthetic and real-world datasets.

APA, Harvard, Vancouver, ISO, and other styles

26

Faber, Felix A., Anders S. Christensen, Bing Huang, and O. Anatole von Lilienfeld. "Alchemical and structural distribution based representation for universal quantum machine learning." Journal of Chemical Physics 148, no. 24 (June 28, 2018): 241717. http://dx.doi.org/10.1063/1.5020710.

Full text

APA, Harvard, Vancouver, ISO, and other styles

27

He, Xiaoxu, Stephanie Leung, James Warrington, Olga Shmuilovich, and Shuo Li. "Automated neural foraminal stenosis grading via task-aware structural representation learning." Neurocomputing 287 (April 2018): 185–95. http://dx.doi.org/10.1016/j.neucom.2018.01.088.

Full text

APA, Harvard, Vancouver, ISO, and other styles

28

Nguyen, Thanh Toan, Minh Tam Pham, Thanh Tam Nguyen, Thanh Trung Huynh, Van Vinh Tong, Quoc Viet Hung Nguyen, and Thanh Tho Quan. "Structural representation learning for network alignment with self-supervised anchor links." Expert Systems with Applications 165 (March 2021): 113857. http://dx.doi.org/10.1016/j.eswa.2020.113857.

Full text

APA, Harvard, Vancouver, ISO, and other styles

29

Garber, Dominik, and József Fiser. "The effect of emerging structural representation on spatial visual statistical learning." Journal of Vision 22, no. 14 (December 5, 2022): 3514. http://dx.doi.org/10.1167/jov.22.14.3514.

Full text

APA, Harvard, Vancouver, ISO, and other styles

30

Liu, Cuiwei, Zhaokui Li, Xiangbin Shi, and Chong Du. "Learning a Mid-Level Representation for Multiview Action Recognition." Advances in Multimedia 2018 (2018): 1–10. http://dx.doi.org/10.1155/2018/3508350.

Full text

Abstract:

Recognizing human actions in videos is an active topic with broad commercial potentials. Most of the existing action recognition methods are supposed to have the same camera view during both training and testing. And thus performances of these single-view approaches may be severely influenced by the camera movement and variation of viewpoints. In this paper, we address the above problem by utilizing videos simultaneously recorded from multiple views. To this end, we propose a learning framework based on multitask random forest to exploit a discriminative mid-level representation for videos from multiple cameras. In the first step, subvolumes of continuous human-centered figures are extracted from original videos. In the next step, spatiotemporal cuboids sampled from these subvolumes are characterized by multiple low-level descriptors. Then a set of multitask random forests are built upon multiview cuboids sampled at adjacent positions and construct an integrated mid-level representation for multiview subvolumes of one action. Finally, a random forest classifier is employed to predict the action category in terms of the learned representation. Experiments conducted on the multiview IXMAS action dataset illustrate that the proposed method can effectively recognize human actions depicted in multiview videos.

APA, Harvard, Vancouver, ISO, and other styles

31

Shi, Ying, Yan Zhao, and Nian Mao Deng. "Robust Object Tracking Based on Structural Local Sparse Representation and Incremental Subspace Learning." Advanced Materials Research 765-767 (September 2013): 2388–92. http://dx.doi.org/10.4028/www.scientific.net/amr.765-767.2388.

Full text

Abstract:

We develop a robust tracking method based on the structural local sparse representation and incremental subspace learning. This representation exploits both partial information and spatial information of the target. The similarity obtained by pooling across the local patches helps locate the target more accurately. In addition, we develop a template update method which combines incremental subspace learning and sparse representation. This strategy adapts the template to the appearance change of the target with less drifting and reduces the influence of the occluded target template as well. Experiments on challenging sequences with evaluation of the state-of-the-art methods show effectiveness of the proposed algorithm.

APA, Harvard, Vancouver, ISO, and other styles

32

Jafariakinabad, Fereshteh, and Kien A. Hua. "A Self-Supervised Representation Learning of Sentence Structure for Authorship Attribution." ACM Transactions on Knowledge Discovery from Data 16, no. 4 (August 31, 2022): 1–16. http://dx.doi.org/10.1145/3491203.

Full text

Abstract:

The syntactic structure of sentences in a document substantially informs about its authorial writing style. Sentence representation learning has been widely explored in recent years and it has been shown that it improves the generalization of different downstream tasks across many domains. Even though utilizing probing methods in several studies suggests that these learned contextual representations implicitly encode some amount of syntax, explicit syntactic information further improves the performance of deep neural models in the domain of authorship attribution. These observations have motivated us to investigate the explicit representation learning of syntactic structure of sentences. In this article, we propose a self-supervised framework for learning structural representations of sentences. The self-supervised network contains two components; a lexical sub-network and a syntactic sub-network which take the sequence of words and their corresponding structural labels as the input, respectively. Due to the n -to-1 mapping of words to their structural labels, each word will be embedded into a vector representation which mainly carries structural information. We evaluate the learned structural representations of sentences using different probing tasks, and subsequently utilize them in the authorship attribution task. Our experimental results indicate that the structural embeddings significantly improve the classification tasks when concatenated with the existing pre-trained word embeddings.

APA, Harvard, Vancouver, ISO, and other styles

33

Iuchi, Hitoshi, Taro Matsutani, Keisuke Yamada, Natsuki Iwano, Shunsuke Sumi, Shion Hosoda, Shitao Zhao, Tsukasa Fukunaga, and Michiaki Hamada. "Representation learning applications in biological sequence analysis." Computational and Structural Biotechnology Journal 19 (2021): 3198–208. http://dx.doi.org/10.1016/j.csbj.2021.05.039.

Full text

APA, Harvard, Vancouver, ISO, and other styles

34

Chen, C. L. Philip, Zhulin Liu, and Shuang Feng. "Universal Approximation Capability of Broad Learning System and Its Structural Variations." IEEE Transactions on Neural Networks and Learning Systems 30, no. 4 (April 2019): 1191–204. http://dx.doi.org/10.1109/tnnls.2018.2866622.

Full text

APA, Harvard, Vancouver, ISO, and other styles

35

Ye, Zhonglin, Haixing Zhao, Ke Zhang, Yu Zhu, and Zhaoyang Wang. "An Optimized Network Representation Learning Algorithm Using Multi-Relational Data." Mathematics 7, no. 5 (May 21, 2019): 460. http://dx.doi.org/10.3390/math7050460.

Full text

Abstract:

Representation learning aims to encode the relationships of research objects into low-dimensional, compressible, and distributed representation vectors. The purpose of network representation learning is to learn the structural relationships between network vertices. Knowledge representation learning is oriented to model the entities and relationships in knowledge bases. In this paper, we first introduce the idea of knowledge representation learning into network representation learning, namely, we propose a new approach to model the vertex triplet relationships based on DeepWalk without TransE. Consequently, we propose an optimized network representation learning algorithm using multi-relational data, MRNR, which introduces the multi-relational data between vertices into the procedures of network representation learning. Importantly, we adopted a kind of higher order transformation strategy to optimize the learnt network representation vectors. The purpose of MRNR is that multi-relational data (triplets) can effectively guide and constrain the procedures of network representation learning. The experimental results demonstrate that the proposed MRNR can learn the discriminative network representations, which show better performance on network classification, visualization, and case study tasks compared to the proposed baseline algorithms in this paper.

APA, Harvard, Vancouver, ISO, and other styles

36

Nido, Gonzalo S., Ludovica Bachschmid-Romano, Ugo Bastolla, and Alberto Pascual-García. "Learning structural bioinformatics and evolution with a snake puzzle." PeerJ Computer Science 2 (December 5, 2016): e100. http://dx.doi.org/10.7717/peerj-cs.100.

Full text

Abstract:

We propose here a working unit for teaching basic concepts of structural bioinformatics and evolution through the example of a wooden snake puzzle, strikingly similar to toy models widely used in the literature of protein folding. In our experience, developed at a Master’s course at the Universidad Autónoma de Madrid (Spain), the concreteness of this example helps to overcome difficulties caused by the interdisciplinary nature of this field and its high level of abstraction, in particular for students coming from traditional disciplines. The puzzle will allow us discussing a simple algorithm for finding folded solutions, through which we will introduce the concept of the configuration space and the contact matrix representation. This is a central tool for comparing protein structures, for studying simple models of protein energetics, and even for a qualitative discussion of folding kinetics, through the concept of the Contact Order. It also allows a simple representation of misfolded conformations and their free energy. These concepts will motivate evolutionary questions, which we will address by simulating a structurally constrained model of protein evolution, again modelled on the snake puzzle. In this way, we can discuss the analogy between evolutionary concepts and statistical mechanics that facilitates the understanding of both concepts. The proposed examples and literature are accessible, and we provide supplementary material (see ‘Data Availability’) to reproduce the numerical experiments. We also suggest possible directions to expand the unit. We hope that this work will further stimulate the adoption of games in teaching practice.

APA, Harvard, Vancouver, ISO, and other styles

37

Sun, Wei-Xiang, and Hui Xue. "Learning graph-level representation from local-structural distribution with Graph Neural Networks." Knowledge-Based Systems 230 (October 2021): 107383. http://dx.doi.org/10.1016/j.knosys.2021.107383.

Full text

APA, Harvard, Vancouver, ISO, and other styles

38

Li, Ao, Xin Liu, Yanbing Wang, Deyun Chen, Kezheng Lin, Guanglu Sun, and Hailong Jiang. "Subspace structural constraint-based discriminative feature learning via nonnegative low rank representation." PLOS ONE 14, no. 5 (May 7, 2019): e0215450. http://dx.doi.org/10.1371/journal.pone.0215450.

Full text

APA, Harvard, Vancouver, ISO, and other styles

39

Wang, Jing, Shubin Lyu, Junwei Duan, and Zhengchun Lin. "Sparse Enhancement Fuzzy Broad Learning System Based on Multiple Clustering Methods." Journal of Physics: Conference Series 2203, no. 1 (February 1, 2022): 012068. http://dx.doi.org/10.1088/1742-6596/2203/1/012068.

Full text

Abstract:

Abstract The fuzzy broad learning system (FBLS) is a novel, neuro-fuzzy model. Different from other neuro-fuzzy models with low efficiency, FBLS can obtain better performance using less computation time. However, the clustering-based fuzzy rule generation approach makes the performance of FBLS limited. Meanwhile, it is unknown how the enhancement layers from FBLS contribute to the model performance, which hinders the further extension of the model structure. To solve these problems, we propose a sparse enhancement fuzzy broad learning system (SEFBLS). It uses only a sparse set of enhancement nodes to replace the original enhancement node groups. To obtain a better representation, the designed principal component-based sparse autoencoder is used for feature reconstruction and information removal. In addition, to explore the optimal model structure and performance, multiple clustering methods (fuzzy and non-fuzzy) are used to improve SEFBLS. The results on 10 UCI classification datasets show that the proposed SEFBLS obtains competitive accuracy using fewer fuzzy rules.

APA, Harvard, Vancouver, ISO, and other styles

40

Xiao, Yabo, Dongdong Yu, Xiao Juan Wang, Lei Jin, Guoli Wang, and Qian Zhang. "Learning Quality-Aware Representation for Multi-Person Pose Regression." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 3 (June 28, 2022): 2822–30. http://dx.doi.org/10.1609/aaai.v36i3.20186.

Full text

Abstract:

Off-the-shelf single-stage multi-person pose regression methods generally leverage the instance score (i.e., confidence of the instance localization) to indicate the pose quality for selecting the pose candidates. We consider that there are two gaps involved in existing paradigm: 1) The instance score is not well interrelated with the pose regression quality. 2) The instance feature representation, which is used for predicting the instance score, does not explicitly encode the structural pose information to predict the reasonable score that represents pose regression quality. To address the aforementioned issues, we propose to learn the pose regression quality-aware representation. Concretely, for the first gap, instead of using the previous instance confidence label (e.g., discrete {1,0} or Gaussian representation) to denote the position and confidence for person instance, we firstly introduce the Consistent Instance Representation (CIR) that unifies the pose regression quality score of instance and the confidence of background into a pixel-wise score map to calibrates the inconsistency between instance score and pose regression quality. To fill the second gap, we further present the Query Encoding Module (QEM) including the Keypoint Query Encoding (KQE) to encode the positional and semantic information for each keypoint and the Pose Query Encoding (PQE) which explicitly encodes the predicted structural pose information to better fit the Consistent Instance Representation (CIR). By using the proposed components, we significantly alleviate the above gaps. Our method outperforms previous single-stage regression-based even bottom-up methods and achieves the state-of-the-art result of 71.7 AP on MS COCO test-dev set.

APA, Harvard, Vancouver, ISO, and other styles

41

Zhou, Xiaojie, Pengjun Zhai, and Yu Fang. "Learning Description-Based Representations for Temporal Knowledge Graph Reasoning via Attentive CNN." Journal of Physics: Conference Series 2025, no. 1 (September 1, 2021): 012003. http://dx.doi.org/10.1088/1742-6596/2025/1/012003.

Full text

Abstract:

Abstract Knowledge graphs have played a significant role in various applications and knowledge reasoning is one of the key tasks. However, the task gets more challenging when each fact is associated with a time annotation on temporal knowledge graph. Most of the existing temporal knowledge graph representation learning methods exploit structural information to learn the entity and relation representations. By these methods, those entities with similar structural information cannot be easily distinguished. Incorporating other information is an effective way to solve such problems. To address this problem, we propose a temporal knowledge graph representation learning method d-HyTE that incorporates entity descriptions. We learn structure-based representations of entities and relations and explore a deep convolutional neural network with attention to encode description-based representations of entities. The joint representation of two different representations of an entity is regarded as the final representation. We evaluate this method on link prediction and temporal scope prediction. Experimental results showed that our method d-HyTE outperformed the other baselines on many metrics.

APA, Harvard, Vancouver, ISO, and other styles

42

Minematsu, Nobuaki. "Structural representation of the pronunciation and its application to computer‐aided language learning." Journal of the Acoustical Society of America 120, no. 5 (November 2006): 3137–38. http://dx.doi.org/10.1121/1.4787745.

Full text

APA, Harvard, Vancouver, ISO, and other styles

43

Zhang, Weihang, Ovidiu Șerban, Jiahao Sun, and Yike Guo. "IPPT4KRL: Iterative Post-Processing Transfer for Knowledge Representation Learning." Machine Learning and Knowledge Extraction 5, no. 1 (January 6, 2023): 43–58. http://dx.doi.org/10.3390/make5010004.

Full text

Abstract:

Knowledge Graphs (KGs), a structural way to model human knowledge, have been a critical component of many artificial intelligence applications. Many KG-based tasks are built using knowledge representation learning, which embeds KG entities and relations into a low-dimensional semantic space. However, the quality of representation learning is often limited by the heterogeneity and sparsity of real-world KGs. Multi-KG representation learning, which utilizes KGs from different sources collaboratively, presents one promising solution. In this paper, we propose a simple, but effective iterative method that post-processes pre-trained knowledge graph embedding (IPPT4KRL) on individual KGs to maximize the knowledge transfer from another KG when a small portion of alignment information is introduced. Specifically, additional triples are iteratively included in the post-processing based on their adjacencies to the cross-KG alignments to refine the pre-trained embedding space of individual KGs. We also provide the benchmarking results of existing multi-KG representation learning methods on several generated and well-known datasets. The empirical results of the link prediction task on these datasets show that the proposed IPPT4KRL method achieved comparable and even superior results when compared against more complex methods in multi-KG representation learning.

APA, Harvard, Vancouver, ISO, and other styles

44

Zhang, Liyan, Jingfeng Guo, Jiazheng Wang, Jing Wang, Shanshan Li, and Chunying Zhang. "Hypergraph and Uncertain Hypergraph Representation Learning Theory and Methods." Mathematics 10, no. 11 (June 3, 2022): 1921. http://dx.doi.org/10.3390/math10111921.

Full text

Abstract:

With the advent of big data and the information age, the data magnitude of various complex networks is growing rapidly. Many real-life situations cannot be portrayed by ordinary networks, while hypergraphs have the ability to describe and characterize higher order relationships, which have attracted extensive attention from academia and industry in recent years. Firstly, this paper described the development process, the application areas, and the existing review research of hypergraphs; secondly, introduced the theory of hypergraphs briefly; then, compared the learning methods of ordinary graphs and hypergraphs from three aspects: matrix decomposition, random walk, and deep learning; next, introduced the structural optimization of hypergraphs from three perspectives: dynamic hypergraphs, hyperedge weight optimization, and multimodal hypergraph generation; after that, the applicability of three uncertain hypergraph models were analyzed based on three uncertainty theories: probability theory, fuzzy set, and rough set; finally, the future research directions of hypergraphs and uncertain hypergraphs were prospected.

APA, Harvard, Vancouver, ISO, and other styles

45

Mu, Shanlei, Yaliang Li, Wayne Xin Zhao, Siqing Li, and Ji-Rong Wen. "Knowledge-Guided Disentangled Representation Learning for Recommender Systems." ACM Transactions on Information Systems 40, no. 1 (January 31, 2022): 1–26. http://dx.doi.org/10.1145/3464304.

Full text

Abstract:

In recommender systems, it is essential to understand the underlying factors that affect user-item interaction. Recently, several studies have utilized disentangled representation learning to discover such hidden factors from user-item interaction data, which shows promising results. However, without any external guidance signal, the learned disentangled representations lack clear meanings, and are easy to suffer from the data sparsity issue. In light of these challenges, we study how to leverage knowledge graph (KG) to guide the disentangled representation learning in recommender systems. The purpose for incorporating KG is twofold, making the disentangled representations interpretable and resolving data sparsity issue. However, it is not straightforward to incorporate KG for improving disentangled representations, because KG has very different data characteristics compared with user-item interactions. We propose a novel K nowledge-guided D isentangled R epresentations approach ( KDR ) to utilizing KG to guide the disentangled representation learning in recommender systems. The basic idea, is to first learn more interpretable disentangled dimensions (explicit disentangled representations) based on structural KG, and then align implicit disentangled representations learned from user-item interaction with the explicit disentangled representations. We design a novel alignment strategy based on mutual information maximization. It enables the KG information to guide the implicit disentangled representation learning, and such learned disentangled representations will correspond to semantic information derived from KG. Finally, the fused disentangled representations are optimized to improve the recommendation performance. Extensive experiments on three real-world datasets demonstrate the effectiveness of the proposed model in terms of both performance and interpretability.

APA, Harvard, Vancouver, ISO, and other styles

46

Bin, Chenzhong, Saige Qin, Guanjun Rao, Tianlong Gu, and Liang Chang. "Multiview Translation Learning for Knowledge Graph Embedding." Scientific Programming 2020 (August 25, 2020): 1–9. http://dx.doi.org/10.1155/2020/7084958.

Full text

Abstract:

Recently, knowledge graph embedding methods have attracted numerous researchers’ interest due to their outstanding effectiveness and robustness in knowledge representation. However, there are still some limitations in the existing methods. On the one hand, translation-based representation models focus on conceiving translation principles to represent knowledge from a global perspective, while they fail to learn various types of relational facts discriminatively. It is prone to make the entity congestion of complex relational facts in the embedding space reducing the precision of representation vectors associating with entities. On the other hand, parallel subgraphs extracted from the original graph are used to learn local relational facts discriminatively. However, it probably causes the relational fact damage of the original knowledge graph to some degree during the subgraph extraction. Thus, previous methods are unable to learn local and global knowledge representation uniformly. To that end, we propose a multiview translation learning model, named MvTransE, which learns relational facts from global-view and local-view perspectives, respectively. Specifically, we first construct multiple parallel subgraphs from an original knowledge graph by considering entity semantic and structural features simultaneously. Then, we embed the original graph and construct subgraphs into the corresponding global and local feature spaces. Finally, we propose a multiview fusion strategy to integrate multiview representations of relational facts. Extensive experiments on four public datasets demonstrate the superiority of our model in knowledge graph representation tasks compared to state-of-the-art methods.

APA, Harvard, Vancouver, ISO, and other styles

47

Rosafalco, Luca, Andrea Manzoni, Stefano Mariani, and Alberto Corigliano. "An Autoencoder-Based Deep Learning Approach for Load Identification in Structural Dynamics." Sensors 21, no. 12 (June 19, 2021): 4207. http://dx.doi.org/10.3390/s21124207.

Full text

Abstract:

In civil engineering, different machine learning algorithms have been adopted to process the huge amount of data continuously acquired through sensor networks and solve inverse problems. Challenging issues linked to structural health monitoring or load identification are currently related to big data, consisting of structural vibration recordings shaped as a multivariate time series. Any algorithm should therefore allow an effective dimensionality reduction, retaining the informative content of data and inferring correlations within and across the time series. Within this framework, we propose a time series AutoEncoder (AE) employing inception modules and residual learning for the encoding and the decoding parts, and an extremely reduced latent representation specifically tailored to tackle load identification tasks. We discuss the choice of the dimensionality of this latent representation, considering the sources of variability in the recordings and the inverse-forward nature of the AE. To help setting the aforementioned dimensionality, the false nearest neighbor heuristics is also exploited. The reported numerical results, related to shear buildings excited by dynamic loadings, highlight the signal reconstruction capacity of the proposed AE, and the capability to accomplish the load identification task.

APA, Harvard, Vancouver, ISO, and other styles

48

Usher, Bethany, and Stephanie Hazel. "Students as scholars courses and student learning outcomes: A realignment." Innovations in Teaching & Learning Conference Proceedings 8 (July 15, 2016): 2. http://dx.doi.org/10.13021/g8gs31.

Full text

Abstract:

During the summer, a group of faculty will be looking at the Students as Scholars student learning outcomes and course definitions. After five years, we have seen that some of the elements are too broad or too narrow, and that the course descriptions are difficult understand. My expectation is that, at the least, there will be a simplification in the elements of the student learning outcomes. This poster will be a visual representation of those changes, presented as a part of a campus-wide discussion of any changes. I will provide a full abstract of the poster at the end of the summer.

APA, Harvard, Vancouver, ISO, and other styles

49

Jarosz, Gaja. "Computational Modeling of Phonological Learning." Annual Review of Linguistics 5, no. 1 (January 14, 2019): 67–90. http://dx.doi.org/10.1146/annurev-linguistics-011718-011832.

Full text

Abstract:

Recent advances in computational modeling have led to significant discoveries about the representation and acquisition of phonological knowledge and the limits on language learning and variation. These discoveries are the result of applying computational learning models to increasingly rich and complex natural language data while making increasingly realistic assumptions about the learning task. This article reviews the recent developments in computational modeling that have made connections between fully explicit theories of learning, naturally occurring corpus data, and the richness of psycholinguistic and typological data possible. These advances fall into two broad research areas: ( a) the development of models capable of learning the quantitative, noisy, and inconsistent patterns that are characteristic of naturalistic data and ( b) the development of models with the capacity to learn hidden phonological structure from unlabeled data. After reviewing these advances, the article summarizes some of the most significant consequent discoveries.

APA, Harvard, Vancouver, ISO, and other styles

50

Kuok, Sin-Chi, and Ka-Veng Yuen. "Model-free data reconstruction of structural response and excitation via sequential broad learning." Mechanical Systems and Signal Processing 141 (July 2020): 106738. http://dx.doi.org/10.1016/j.ymssp.2020.106738.

Full text

APA, Harvard, Vancouver, ISO, and other styles

Journal articles on the topic 'Broad Structural Representation Learning'

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles