Multiview learning with twin parametric margin SVM

Self-taught Multi-view Spectral Clustering

A deep multi-view imbalanced learning approach for identifying informative COVID-19 tweets from social media

Language Impairment (LI) is a developmental disorder that mainly manifests impaired language learning and processing. Evidence, largely from English-speaking population studies, has shown that children with LI compared to typically developing (TD) children have low scores in sequential learning tasks but similar performance in declarative learning tasks. According to the declarative/procedural model, LI children compensate for their deficiency in syntactic skills (i.e., deficits in the procedural memory system) by using the declarative memory system (indispensable for vocabulary acquisition). Although there are specific deficits in children with LI depending on the language they speak, it is assumed that this model can explain the shortcomings of such pathology regardless of the language spoken. In the current study, we compared the performance of fifteen school-aged Mexican Spanish-speaking children with LI and twenty TD children during sequential and declarative learning tasks and then analyzed the relationship between their performance in these tasks and their abilities in syntax and semantics. Children with LI displayed lower scores than normal children in the sequential learning task, but no differences were found in declarative learning performance with verbal or visual stimuli. No significant correlations were observed in children with LI between their performance in sequential learning and their abilities in semantics and no significant correlations were observed in TD children between their performance in sequential learning and their abilities in syntax. In contrast, for children with LI, a significant correlation between their performance in declarative learning and their abilities in semantics was observed and for the group of TD children a significant correlation between their performance in declarative learning and their abilities in syntax was observed. This study shows that Spanish-speaking children with LI display a pattern of learning impairment that supports the declarative/procedural model hypothesis. However, they display poor verbal declarative learning skills, probably due to low verbal working memory capacity.

Noises and outliers often degrade the final prediction performance in practical data processing. Multi-view learning by integrating complementary information across heterogeneous modalities has become one of the core techniques in the field of machine learning. However, existing methods rely on explicit-view clustering and stringent alignment assumptions, which affect the effectiveness in addressing the challenges such as inconsistencies between views, noise interference, and misalignment across different views. To alleviate these issues, we present a latent multi-view representation learning model based on low-rank embedding by implicitly uncovering the latent consistency structure of data, which allows us to achieve robust and efficient multi-view feature fusion. In particular, we utilize low-rank constraints to construct a unified latent subspace representation and introduce an adaptive noise suppression mechanism that significantly enhances robustness against outliers and noise interference. Moreover, the Augmented Lagrangian Multiplier Alternating Direction Minimization (ALM-ADM) framework enables efficient optimization of the proposed method. Experimental results on multiple benchmark datasets demonstrate that the proposed approach outperforms existing state-of-the-art methods in both clustering performance and robustness.

New skills may be learned from the outcomes of their own internally generated actions (experiential learning) or from the observation of the consequences of externally generated actions (observational learning). Observational learning requires the coordination of cognitive functions and the processing of social information. Due to the “social” abilities underlying observational learning, the study of this process in individuals with limited social abilities such as those affected by Autism Spectrum Disorders (ASD) is worthy of being investigated. We asked a group of 16 low-functioning young children with ASD and group of 16 sex- and mental age-matched typically developing (TD) children to build a house with a set of bricks after a video-demonstration showing an actor who built the house (observational task – OBS task) and then to build by trial and error another house (experiential task – EXP task). For ASD group, performances in learning tasks were correlated with measures of cortical thickness of specific Regions of Interest (ROI) and volume of deep gray matter structures known to be related with such kinds of learning. According to our a priori hypothesis, for OBS task we selected the following ROI: frontal lobe (pars opercularis, pars triangularis, and premotor area), parietal lobe (inferior parietal gyrus), temporal lobe (superior temporal gyrus), cerebellar hemispheres. For EXP task, we selected the following ROI: precentral frontal gyrus and superior frontal gyrus, cerebellar hemispheres, basal ganglia, thalamus. Although performances of ASD and TD children improved in both OBS and EXP tasks, children with ASD obtained lower scores of goal achievement than TD children in both learning tasks. Only in ASD group, goal achievement scores positively correlated with hyperimitations indicating that children with ASD tended to have a “copy-all” approach that facilitated the goal achievement. Moreover, the marked hyperimitative tendencies of children with ASD were positively associated with the thickness of left pars opercularis, left premotor area, and right superior temporal gyrus, areas belonging to mirror neuron system, and with the volume of both cerebellar hemispheres. These findings suggest that in children with ASD the hyperimitation can represent a learning strategy that might be related to the mirror neuron system.

Experience and the Development of Adaptive Behavior

Adult male Wistar rats were implanted bilateraly with bipolar electrodes in substantia nigra-ventral tegmental area (SN-VTA) to experience intracranial self-stimulation (ICSS) for 15 min per day over a period of 10 days. These rats were then assessed for the acquisition and performance of the operant and the spatial learning tasks. ICSS experienced rats showed rapid acquisition of both the operant and the spatial learning tasks. Both the lever press performance for 7 sessions in the operant learning task and mean number of alternations per session in the spatial learning task were significantly higher (p < .001) in ICSS experienced rats compared with controls. The results suggest that prior ICSS experience facilitates the acquisition and performance in both the operant and the spatial learning tasks, which may be due to the structural and neurochemical alterations in the hippocampus induced by ICSS experience.

The cross-lingual text classification task remains a long-standing challenge that aims to train a classifier on high-resource source languages and apply it to classify texts in low-resource target languages, bridging linguistic gaps while maintaining accuracy. Most existing methods achieve exceptional performance by relying on multilingual pretrained language models to transfer knowledge across languages. However, little attention has been paid to factors beyond semantic similarity, which leads to the degradation of classification performance in the target languages. This study proposes a novel framework, a heterogeneous graph neural network with multi-view contrastive learning for cross-lingual text classification, which integrates a heterogeneous graph architecture with multi-view contrastive learning for the cross-lingual text classification task. This study constructs a heterogeneous graph to capture both syntactic and semantic knowledge by connecting document and word nodes using different types of edges, including Part-of-Speech tagging, dependency, similarity, and translation edges. A Graph Attention Network is applied to aggregate information from neighboring nodes. Furthermore, this study devises a multi-view contrastive learning strategy to enhance model performance by pulling positive examples closer together and pushing negative examples further apart. Extensive experiments show that the framework outperforms the previous state-of-the-art model, achieving improvements of 2.20% in accuracy and 1.96% in F1-score on the XGLUE and Amazon Review datasets, respectively. These findings demonstrate that the proposed model makes a positive impact on the cross-lingual text classification task overall.

Behavioral performance altering effects of MK-801 in zebrafish ( Danio rerio)

Aim/Purpose: This study aims to analyze the cognitive load experienced by secondary school students in Biology within m-learning environments and its impact on learning performance. Background: Cognitive load has become a critical issue that schools need to address to ensure students can excel in their learning without being overwhelmed. While principles for reducing cognitive load have been extensively discussed in previous research, studies focusing on mobile learning (m-learning) for Biology among students in Malaysia remain limited. This study employed Cognitive Load Theory (CLT) and Cognitive Theory of Multimedia Learning (CTML) to address this gap. By integrating four key principles—segmenting and pretraining, modality, redundancy, and seductive details—into m-learning tasks using the Successive Approximation Model (SAM1), this study aimed to reduce cognitive load and enhance students’ learning performance. Methodology: This study employed a quantitative approach using a randomized pre-test/post-test quasi-experimental design. Students were randomly assigned to either an intervention group (20 students) or a control group (18 students). The study was conducted over four weeks, comprising a three-week intervention period with a one-week interval. Statistical analyses, including independent t-tests, Mann-Whitney U tests, Quade ANCOVA, and Pearson correlation, were used to analyze the quantitative data. Qualitative feedback was analyzed using thematic analysis. Contribution: This study contributes by providing instructional design strategies that incorporate principles for reducing cognitive load in mobile learning for Biology. It also demonstrates how Cognitive Load Theory (CLT) and Cognitive Theory of Multimedia Learning (CTML) can be effectively integrated. By examining the cognitive load experienced by secondary school students in m-learning environments, the study offers valuable insights for designing and implementing effective instructional strategies. Identifying the factors influencing cognitive load enables educators to develop targeted interventions that enhance learning experiences and optimize performance. Findings: The study indicated that the adoption of mobile learning tasks not only significantly reduced cognitive load but also corresponded to enhanced learning performance. Participants engaging in m-learning experienced lower cognitive load, which was positively associated with superior performance in learning tasks, emphasizing the beneficial impact of mobile learning on cognitive load management and academic achievement. Recommendations for Practitioners: Educators and instructional designers are encouraged to incorporate cognitive load principles into their instructional strategies and learning material design to enhance student performance. Policymakers should consider similar strategies to reduce the cognitive load for students in educational settings to improve learning outcomes. Recommendation for Researchers: Researchers are encouraged to replicate the design elements used in this study when developing mobile or online learning materials to reduce learners’ cognitive load and enhance their performance. They should also consider expanding this research to other topics, subjects, and educational levels to provide further insights and validate the effectiveness of these design elements across different contexts. Impact on Society: The findings of this study have significant implications for society, particularly in addressing mental health and stress issues among the younger generation. By identifying strategies to manage cognitive load and reduce stress in online learning environments, the study provides valuable insights for educators, parents, and policymakers. These strategies can help mitigate the adverse effects of cognitive overload, improve learning experiences, and promote better mental well-being. Additionally, the study’s recommendations can guide the development of more effective and supportive learning environments, contributing to overall societal well-being and academic success. Future Research: Future studies could explore cognitive load beyond the intrinsic and extraneous components focused on in this study, examining additional elements within the frameworks of cognitive load theory and multimedia learning. In addition to using the cognitive load questionnaire, exploring other measurement tools could ensure a more comprehensive understanding of cognitive load. Future research might also consider enriching mobile learning tasks by diversifying subject matter and conducting longitudinal cohort studies. Such studies could provide valuable insights into memory retention over extended periods, aiding in optimizing mobile learning frameworks and enhancing educational experiences.

NF-κB activity affects learning in aversive tasks: Possible actions via modulation of the stress axis

Congenital amusia is a lifelong disorder whereby individuals have pervasive difficulties in perceiving and producing music. In contrast, typical individuals display a sophisticated understanding of musical structure, even in the absence of musical training. Previous research has shown that they acquire this knowledge implicitly, through exposure to music's statistical regularities. The present study tested the hypothesis that congenital amusia may result from a failure to internalize statistical regularities – specifically, lower-order transitional probabilities. To explore the specificity of any potential deficits to the musical domain, learning was examined with both tonal and linguistic material. Participants were exposed to structured tonal and linguistic sequences and, in a subsequent test phase, were required to identify items which had been heard in the exposure phase, as distinct from foils comprising elements that had been present during exposure, but presented in a different temporal order. Amusic and control individuals showed comparable learning, for both tonal and linguistic material, even when the tonal stream included pitch intervals around one semitone. However analysis of binary confidence ratings revealed that amusic individuals have less confidence in their abilities and that their performance in learning tasks may not be contingent on explicit knowledge formation or level of awareness to the degree shown in typical individuals. The current findings suggest that the difficulties amusic individuals have with real-world music cannot be accounted for by an inability to internalize lower-order statistical regularities but may arise from other factors.

Yerkes-Dodson law suggests an optimal level of arousal for the best performance in learning tasks. Ideally, the instructors’ expectations should match the abilities and inabilities of students. This study proposes a theory that challenges students optimally and continually over the course of teaching and learning, with proofs using both theoretical and classroom examples. The theory of sustained optimal challenge facilitates student learning by achieving primarily three objectives: (1) continually adjusts the speed and content difficulty levels over the course of teaching and learning; (2) matches the instructors’ expectations with the students’ aptitudes (abilities and inabilities); and (3) finally, reduces the variation in student learning. The effect of central limit theorem, teaching and learning theories, learning outcomes, and student feedback supported the proposed theory in a wide range of disciplines, including, Statistics, Mechanics, Quality, and Ergonomics. Sustained optimal challenges were observed in most courses taught utilizing the proposed theory.

Multi-view semi-supervised learning for classification on dynamic networks

Semantically consistent multi-view representation learning