Dynamic Learning Research Articles

Learning with filopodia and spines: Complementary strong and weak competition lead to specialized, graded, and protected receptive fields.

Filopodia are thin synaptic protrusions that have been long known to play an important role in early development. It has recently been found that they are more abundant in the adult cortex than previously thought, and more plastic than spines (button-shaped mature synapses). Inspired by these findings, we introduce a new model of synaptic plasticity that jointly describes learning of filopodia and spines. The model assumes that filopodia exhibit strongly competitive learning dynamics -similarly to additive spike-timing-dependent plasticity (STDP). At the same time it proposes that, if filopodia undergo sufficient potentiation, they consolidate into spines. Spines follow weakly competitive learning, classically associated with multiplicative, soft-bounded models of STDP. This makes spines more stable and sensitive to the fine structure of input correlations. We show that our learning rule has a selectivity comparable to additive STDP and represents input correlations as well as multiplicative models of STDP. We also show how it can protect previously formed memories and act as a synaptic consolidation mechanism. Overall, our results can be seen as a phenomenological description of how filopodia and spines could cooperate to overcome the difficulties that strong and weak competition each have.

EfficientTrain++: Generalized Curriculum Learning for Efficient Visual Backbone Training.

The superior performance of modern computer vision backbones (e.g., vision Transformers learned on ImageNet-1K/22K) usually comes with a costly training procedure. This study contributes to this issue by generalizing the idea of curriculum learning beyond its original formulation, i.e., training models using easier-to-harder data. Specifically, we reformulate the training curriculum as a soft-selection function, which uncovers progressively more difficult patterns within each example during training, instead of performing easier-to-harder sample selection. Our work is inspired by an intriguing observation on the learning dynamics of visual backbones: during the earlier stages of training, the model predominantly learns to recognize some 'easier-to-learn' discriminative patterns in the data. These patterns, when observed through frequency and spatial domains, incorporate lower-frequency components, and the natural image contents without distortion or data augmentation. Motivated by these findings, we propose a curriculum where the model always leverages all the training data at every learning stage, yet the exposure to the 'easier-to-learn' patterns of each example is initiated first, with harder patterns gradually introduced as training progresses. To implement this idea in a computationally efficient way, we introduce a cropping operation in the Fourier spectrum of the inputs, enabling the model to learn from only the lower-frequency components. Then we show that exposing the contents of natural images can be readily achieved by modulating the intensity of data augmentation. Finally, we integrate these two aspects and design curriculum learning schedules by proposing tailored searching algorithms. Moreover, we present useful techniques for deploying our approach efficiently in challenging practical scenarios, such as large-scale parallel training, and limited input/output or data pre-processing speed. The resulting method, EfficientTrain++, is simple, general, yet surprisingly effective. As an off-the-shelf approach, it reduces the training time of various popular models (e.g., ResNet, ConvNeXt, DeiT, PVT, Swin, CSWin, and CAFormer) by [Formula: see text] on ImageNet-1K/22K without sacrificing accuracy. It also demonstrates efficacy in self-supervised learning (e.g., MAE). Code is available at: https://github.com/LeapLabTHU/EfficientTrain.

Improving First-Year English-Majored Students’ Speaking Skills through Using Digital Storytelling

This study aims to investigate the effectiveness of digital storytelling on Vietnamese first-year English-majored students' English-speaking learning at a university in Vietnam. In this study, the students were asked to create English-dubbed animated stories with different topics relating to their speaking lessons by using the Movie Adventure application. Methods for data collection were speaking pre-and post-tests, questionnaires, and interviews. The findings revealed that using digital storytelling as a pedagogical tool for practicing English speaking benefited students' speaking ability. The findings also showed that engaging in the content of stories not only encouraged students' motivation but instilled their confidence to speak in English. The results of the given questionnaires and interviews showed that students responded positively to the implementation of digital storytelling, which facilitated learning by allowing learners to interact and collaborate in English. From the results gained, it was concluded that digital storytelling can be used to create a dynamic speaking learning environment that helps students participate actively in their English-speaking lessons during their learning time.

Improving English Language Proficiency through Podcasts: A Multifaceted Educational Approach

This paper probes into the strength of podcasts in building the English language through varied dimensions of a learning approach. The paper sought to establish the applicability of podcasts in the learning of languages among EFL students, given that podcasts are increasingly becoming an informal learning platform. The study was carried out among learners of different age groups and language proficiency levels, and the collection of statistics regarding the use of podcasts within language learning was affected through both quantitative and qualitative data. Important findings indicate that regular use of podcasts can make the process of vocabulary acquisition, listening comprehension, and general proficiency stronger. Such findings support the use of podcasts in gaining better language competence in that it not only presents rich contextual content in an accessible manner but also puts into play learner skills. In effect, the inclusion of podcasts into the learning curriculum has implications that are far-reaching in that it could offer an effective improvement in the traditional methodologies of language learning by enhancing a dynamic and flexible learning environment that meets the needs of all learners. This research paper points out the imperative nature of podcasts in modern educational strategies and suggests their application in a wider context of language learning frameworks to bring about superior linguistic competence.

The synergistic and dynamic relationship between learning design and learning analytics

The synergistic relationship between learning design and learning analytics has the potential for improving learning and teaching in near real-time. The potential for integrating the newly available and dynamic information from ongoing analysis into learning design requires new perspectives on learning and teaching data processing and analysis as well as advanced theories, methods, and tools for supporting dynamic learning design processes. Three perspectives of learning analytics design provide summative, real-time, and predictive insights. In a case study with 3,550 users, the navigation sequence and network graph analysis demonstrate the potential of learning analytics design. The study aims to demonstrate how the analysis of navigation patterns and network graph analysis could inform the learning design of self-guided digital learning experiences. Even with open-ended freedom, only 608 sequences were evidenced by learners out of a potential number of hundreds of millions of sequences. Advancements of learning analytics design have the potential for mapping the cognitive, social and even physical states of the learner and optimise their learning environment on the fly.

As Teachers Not Tourists: Creating Knowledge During a Short-Term Study Abroad Program

Here, I address the call for teacher education programs to feature international elements to help pre-service teachers craft powerful classroom instruction and successfully work with students from culturally diverse backgrounds. I share a qualitative investigation of participants’ experiences during a short-term study abroad program in Japan that explored contemporary disaster preparedness as a result of the Great East Japan Earthquake and Tsunami. The program sponsors, the Japanese Ministry of Foreign Affairs, hoped participants would develop an appreciation for the people and culture of Japan while they learned about disaster preparedness. I wondered if collecting curriculum items during a short-term study abroad program could help social studies pre-service teachers create—not just receive—historical domain knowledge? In Japan, participants collected items to use as featured resources around which they designed classroom activities for secondary students. Their activities demonstrated three levels of second-order historical domain knowledge and two elements of civic competence. This study suggests that pre-service teachers with no previous international experience may require explicit modeling and scaffolding to translate their short-term study abroad participation into dynamic learning. Another implication is that participants need strong support to consider the photographs they capture as artifacts of contemporary material culture.

Academics’ practices and perceptions of career development learning in the curriculum

ABSTRACT Career development learning (CDL) equips students with the skills, knowledge and resources to navigate their careers amidst dynamic work and learning environments. While CDL is known to be facilitated by central careers services in higher education institutions, embedding CDL activities within the curriculum is purported to be an effective approach to generate meaningful reflections that prepare students for their future lives. This study examined academics’ perceptions and applications of CDL to understand the extent to which CDL is currently practiced in the curriculum. At one institution, interviews were conducted with 55 academics teaching across 101 subjects and in various disciplines. Findings demonstrate that most CDL is delivered informally or in isolation without a structured framework, highlighting the need to improve purposeful integration of CDL in the curriculum. Recommendations point to greater adoption of strategic institution-wide approaches to CDL, which ultimately impact students’ employability choices, career decision-making, and preparation for the workforce.

Development and external validation of a multidimensional deep learning model to dynamically predict kidney outcomes in IgA nephropathy.

Accurately predicting kidney outcomes in IgA nephropathy is crucial for clinical decision making. Insufficient use of longitudinal data in previous studies has limited the accuracy and interpretability of prediction models for failing to reflect the chronic nature of IgA nephropathy. This study aimed at establishing a multivariable dynamic deep learning model using comprehensive longitudinal data for the prediction of kidney outcomes in IgA nephropathy. In this retrospective cohort study of 2,056 IgA nephropathy patients at 18 kidney centers, a total of 28,317 data points were collected by the sliding window method. Among them, 15,462 windows in a single center were randomly assigned to training (80%) and validation (20%) sets while 8797 windows in 18 kidney centers were assigned to an independently test set. Interpretable Multi-Variable Long Short-Term Memory (IMV-LSTM), a deep learning model, was implemented to predict kidney outcomes (kidney failure or 50% decline in kidney function) based on time-invariant variables measured at biopsy and time-variant variables measured during follow-up. Risk performance was evaluated using Kaplan-Meier analysis and the C statistic. Trajectory analysis was performed to assess the various trends of clinical variables during follow-up. The model achieved a higher C statistic (0.93; 95% CI, 0.92-0.95) on the test set than the XGBoost prediction model that we developed in a previous study using only baseline information (C statistic, 0.84; 95% CI, 0.80-0.88). Kaplan-Meier analysis showed that groups with lower predicted risks from the full model survived longer than groups with higher risks. Time-variant variables demonstrated higher importance scores than time-invariant variables. Within time-variant variables, more recent measurements showed higher importance scores. Further interpretation showed that certain trajectory groups of time-variant variables such as serum creatinine and urine protein were associated with elevated risks of adverse outcomes. In IgA nephropathy, a deep learning model can be used to accurately and dynamically predict kidney prognosis based on longitudinal data, and time-variant variables show strong ability to predict kidney outcome.

Mycobactin analogue interacting with siderophore efflux-pump protein: insights from molecular dynamics simulations and whole-cell assays

IntroductionIn response to continued public health emergency of antimicrobial resistance (AMR), a significant key strategy is the discovery of novel mycobacterial efflux-pump inhibitors (EPIs) as potential adjuvants in combination drug therapy. Interest in identifying new chemotypes which could potentially synergize with the existing antibiotics and can be deployed as part of a combination therapy. This strategy could delay the emergence of resistance to existing antibiotics and increase their efficacy against resistant strains of mycobacterial species. In recent decades, notable approaches have been accounted for EPI development and have resulted in the discovery of several EPIs including SQ109 and AU1235. In context, to accelerate newer EPIs with novel mode of action here we have discussed mycobactin analogues and highlighted in silico binding orientation with siderophore efflux-pump proteins MmpL4/5.Methods3-(2-hydroxyphenyl)-5-(aryl)-pyrazoline series was investigated for whole-cell efflux-pump inhibitory activity against Mycobacterium smegmatis and Mycobacterium abscessus. Machine learning and molecular dynamics were performed to construct a MmpL4/5 complex embedded in a lipid bilayer to identify the putative binding site and to predict ligand-protein binding energetics. Furthermore, the identified HIT compound was investigated in synergistic assay with bedaquiline.ResultsCompound Il, 2-(5-(4-fluorophenyl)-4,5-dihydro-1H-pyrazol-3-yl)phenol, was identified as the most potent efflux pump inhibitor against M. smegmatis in whole-cell efflux-pump investigation. Followed HIT Il employed against M. abscessus for efflux-pump inhibition investigations and notable whole-cell efflux-pump inhibitory profile has been observed. The theoretical investigations predicted compound Il to be selective towards MmpL4, with significant hydrogen bonding and π-π stacking interactions effectively blocking a critical Asp-Tyr dyad interaction network necessary for proton translocation. Compound Il with bedaquiline highlighted an additive profile against the M. abscessus pathogen.ConclusionsMD simulations and whole-cell assays are indicating potential development of compound Il as an adjunct to the existing therapeutic regimen against mycobacterial infections.

Designing a smart classroom with advanced Audiovisual equipment and soft collaboration capabilities for Higher Education

This is a technology-enabled classroom design which reflects a thoughtful integration of cutting-edge audiovisual solutions to enhance the learning environment. The inclusion of automated audio-visual solutions indicates a commitment to creating a seamless and efficient learning experience through technology. The incorporation of a voice lift application ensures clear and audible communication for the instructor, addressing potential challenges in large classroom settings. The use of Dante-based communication over Ethernet signifies a high-quality and reliable audio distribution system, enabling efficient communication within the classroom. The inclusion of features catering to individuals with disabilities demonstrates a commitment to creating an inclusive and accessible learning environment. The beamforming microphone array system with multiple elements is a sophisticated technology that allows for effective tracking of the active participant. This ensures that the audio focus adapts to the speaker's location. The automatic and steerable coverage type enhances the adaptability of the microphone array system, automatically focusing on the speaker. This feature contributes to an immersive and dynamic learning experience. The support for Power over Ethernet (PoE) simplifies the installation and management of AV devices in the classroom. It reduces the need for additional power outlets and cables, streamlining the overall setup. Overall, this design prioritizes advanced audiovisual technologies to create a unique, state-of-the-art, and inclusive technology-enabled classroom. The focus on clear communication, adaptability, and ease of use demonstrates a commitment to providing an optimal learning environment for both faculty and students

LEARNING TO LEARN: THE KEY TO LEADERSHIP SUCCESS

AbstractThe author is former CEO of 7‐Eleven, Inc., and Blockbuster, Inc., and has been involved at the board level and other key positions in various nonprofits and artistic organizations. He says that in his career, he “grew to appreciate the critical importance of education to the individual, the corporation, and to the humanity at large.” He says that he has tried to “capture ”what″ learnings were necessary, “how” to make leadership a dynamic learning process, and “why” continued learning is such a fundamental requirement for effective leadership. I have distilled the what, how, and why of my leadership education into 9 principles I call the “C‐Suite Learnings.” The three areas of what to learn are, in his words, change, confidence, and clarity. In how to learn, they are critical thinking, curiosity, and creativity. For why to learn, collaboration, cultural literacy, and character. “My goal,” he concludes, “is to help others find their own path to academic, professional, and even personal success. By practicing these nine Cs, we can Live to Learn; freeing ourselves from personal and societal constraints that limit our success. Only then will we truly Learn to Live; and in turn Learn to Lead.”

A bibliometric exploration of infographics as tools for visual literacy in education

The purpose of this paper is to examine how infographics are used in the dynamics of designing or creating in the teaching and learning process. Utilising a bibliometric approach and content analysis, we examined a sample of 760 documents from the Web of Science and Scopus databases with no lower time limit until November 2023. The analyses aimed to identify trends, including main topics, authors, sources, most cited articles, institutional affiliations, and countries in the literature. This bibliometric approach allows for the observation of trends in the educational application of promoting visual literacy through students’ design or creation of infographics in formal and informal learning settings. Initial publications emerged in 2007, gaining momentum from 2014 to the present. The most prolific fields were medical science, chemistry, and computer science. This investigation shows that educational institutions could employ infographics beyond present boundaries to prepare students—particularly Generation Alpha, digital natives—for a data-driven society. Institutions should expand their use of infographics to improve visual literacy and address the changing educational requirements of students in a dynamic learning environment. Overall, this paper provides insights into the readiness of educators and institutions to engage Generation Alpha, the digital natives, through visual literacy and infographics.

Exploring students’ experiences in the dynamic learning program model

This qualitative study, grounded in descriptive phenomenology, investigated the lived experiences of students studying in a private school under the Central Visayan Institute Foundation – Dynamic Learning Program (CVIF-DLP) framework. Through eight focus group discussions involving 62 participants analyzed with the use of thematic analysis, the research explored the advantages, disadvantages, and transformative potential of the CVIF-DLP approach outlined to the three learning domains. Findings revealed that students focus first on the tangible aspects of learning such as learning activity sheet and writing. They also believed that CVIF-DLP has limited special impact on their physical aspects but affects greatly their cognitive and affective aspects. Despite the varied perspectives and encountered challenges, students agreed that the program helps them improve intellectually and personally. It revealed the complex dynamics shaping student learning journeys, emphasizing the need for ongoing program refinement to address student needs effectively. The study offered valuable insights into educational innovation and pedagogical practices, guiding future efforts to enhance the educational experiences of the implementers of CVIF-DLP.

Integrating AI with emotional and social learning in primary education: Developing a holistic adaptive learning ecosystem

This paper highlights the significance, potential benefits, challenges, and proposed solutions associated with integrating AI-driven tools and platforms into SEL initiatives. The importance of integrating AI with SEL in primary education lies in its ability to foster the holistic development of students. By equipping students with the tools to navigate academic challenges, interpersonal relationships, and emotional regulation, schools can create dynamic learning environments that prioritize the whole child. The potential benefits of integrating AI with SEL are manifold. AI-powered adaptive learning platforms can personalize instruction, provide targeted support, and promote the development of emotional intelligence and social skills among students. Additionally, AI-driven tools and platforms can facilitate collaborative learning experiences, promote active engagement, and provide real-time feedback to students and educators. However, the integration of AI with SEL also presents various challenges that must be addressed. Ethical considerations, such as data privacy, algorithmic bias, and the digital divide, require careful attention to ensure equitable access and outcomes for all students. Additionally, educators may lack the necessary knowledge and skills to effectively utilize AI tools and platforms for SEL purposes, highlighting the need for training and professional development programs. To address these challenges, collaborative efforts among educators, policymakers, technologists, and researchers are essential. By working together, stakeholders can develop evidence-based practices and solutions that align with the goals and values of primary education. Training and professional development programs for educators, robust policies and safeguards for the ethical use of AI technologies, and equitable access to technology for all students are critical components of successful integration. Keywords: AI, Learning, Emotions, Social.

Artificial intelligence- image learning and its applications in neurooncology: a review.

Image learning involves using artificial intelligence (AI) to analyse radiological images. Various machine and deeplearning- based techniques have been employed to process images and extract relevant features. These can later be used to detect tumours early and predict their survival based on their grading and classification. Radiomics is now also used to predict genetic mutations and differentiate between tumour progression and treatment-related side effects. These were once completely dependent on invasive procedures like biopsy and histopathology. The use and feasibility of these techniques are now widely being explored in neurooncology to devise more accurate management plans and limit morbidity and mortality. Hence, the future of oncology lies in the exploration of AI-based image learning techniques, which can be applied to formulate management plans based on less invasive diagnostic techniques, earlier detection of tumours, and prediction of prognosis based on radiomic features. In this review, we discuss some of these applications of image learning in current medical dynamics.

Imitation dynamics and the replicator equation

Abstract Evolutionary game theory has impacted many fields of research by providing a mathematical framework for studying the evolution and maintenance of social and moral behaviors. This success is owed in large part to the demonstration that the central equation of this theory -the replicator equation - is the deterministic limit of a stochastic imitation (social learning) dynamics. Here we offer an alternative elementary proof of this result, which holds for the scenario where players compare their instantaneous (not average) payoffs to decide whether to maintain or change their strategies, and only more successful individuals can be imitated.

Unified control of temporal and spatial scales of sensorimotor behavior through neuromodulation of short-term synaptic plasticity.

Neuromodulators have been shown to alter the temporal profile of short-term synaptic plasticity (STP); however, the computational function of this neuromodulation remains unexplored. Here, we propose that the neuromodulation of STP provides a general mechanism to scale neural dynamics and motor outputs in time and space. We trained recurrent neural networks that incorporated STP to produce complex motor trajectories-handwritten digits-with different temporal (speed) and spatial (size) scales. Neuromodulation of STP produced temporal and spatial scaling of the learned dynamics and enhanced temporal or spatial generalization compared to standard training of the synaptic weights in the absence of STP. The model also accounted for the results of two experimental studies involving flexible sensorimotor timing. Neuromodulation of STP provides a unified and biologically plausible mechanism to control the temporal and spatial scales of neural dynamics and sensorimotor behaviors.

Solution of engineering design and truss topology problems with improved forensic-based investigation algorithm based on dynamic oppositional based learning

AbstractThe forensic-based investigation (FBI) is a metaheuristic algorithm inspired by the criminal investigation process. The collaborative efforts of the investigation and pursuit teams demonstrate the FBI’s involvement during the exploitation and exploration phases. When choosing the promising population, the FBI algorithm’s population selection technique focuses on the same region. This research aims to propose a dynamic population selection method for the original FBI and thereby enhance its convergence performance. To achieve this objective, the FBI may employ dynamic oppositional learning (DOL), a dynamic version of the oppositional learning methodology, to dynamically navigate to local minima in various locations. Therefore, the proposed advanced method is named DOLFBI. The performance of DOLFBI on the CEC2019 and CEC2022 benchmark functions is evaluated by comparing it with several other popular metaheuristics in the literature. As a result, DOLFBI yielded the lowest fitness value in 18 of 22 benchmark problems. Furthermore, DOLFBI has shown promising results in solving real-world engineering problems. It can be argued that DOLFBI exhibits the best convergence performance in cantilever beam design, speed reducer, and tension/compression problems. DOLFBI is often utilized in truss engineering difficulties to determine the minimal weight. Its success is comparable to other competitive MAs in the literature. The Wilcoxon signed-rank and Friedman rank tests further confirmed the study’s stability. Convergence and trajectory analyses validate the superior convergence concept of the proposed method. When the proposed study is compared to essential and enhanced MAs, the results show that DOLFBI has a competitive framework for addressing complex optimization problems due to its robust convergence ability compared to other optimization techniques. As a result, DOLFBI is expected to achieve significant success in various optimization challenges, feature selection, and other complex engineering or real-world problems.

Navigating Entrepreneurial Horizons: Students Perspectives Analysis of the Entrepreneurial Competences in Teaching Context

Entrepreneurship education largely influences the social and economic dimensions of many countries. In the framework of development, frequent changes seek to discover the most effective way of adopting and integrating educational services to meet the requirements of the labour market. This paper aims to analyse entrepreneurial competence in a teaching context from the students’ perspectives. The main objective of the research study aims to measure students’ attitudes towards entrepreneurial intentions, as impacted in an entrepreneurial teaching context. Additionally, it seeks to highlight the significance of the entrepreneurial competence of the lecturing team that goes beyond traditional teaching methods and focuses on fostering an educational environment. As entrepreneurial competence guides opportunity identification by combining skills, knowledge, and attributes and developing them into values, it bridges the gap between teaching and learning, preparing the students to cope with the challenges of the entrepreneurial world. The data were gathered by administering a structured questionnaire that focuses on the perspectives of students in the third cycle of study. The disseminated questionnaire included closed-ended questions related to the entrepreneurial education context, the entrepreneurial competence of the lecturing team, and entrepreneurial intentions. The results of this study demonstrate that the relationship between the entrepreneurial competence of lecturers and entrepreneurial education is crucial for fostering a dynamic and effective learning environment to enhance the entrepreneurial intentions of the students.

Dynamic Weighting Translation Transfer Learning for Imbalanced Medical Image Classification

Medical image diagnosis using deep learning has shown significant promise in clinical medicine. However, it often encounters two major difficulties in real-world applications: (1) domain shift, which invalidates the trained model on new datasets, and (2) class imbalance problems leading to model biases towards majority classes. To address these challenges, this paper proposes a transfer learning solution, named Dynamic Weighting Translation Transfer Learning (DTTL), for imbalanced medical image classification. The approach is grounded in information and entropy theory and comprises three modules: Cross-domain Discriminability Adaptation (CDA), Dynamic Domain Translation (DDT), and Balanced Target Learning (BTL). CDA connects discriminative feature learning between source and target domains using a synthetic discriminability loss and a domain-invariant feature learning loss. The DDT unit develops a dynamic translation process for imbalanced classes between two domains, utilizing a confidence-based selection approach to select the most useful synthesized images to create a pseudo-labeled balanced target domain. Finally, the BTL unit performs supervised learning on the reassembled target set to obtain the final diagnostic model. This paper delves into maximizing the entropy of class distributions, while simultaneously minimizing the cross-entropy between the source and target domains to reduce domain discrepancies. By incorporating entropy concepts into our framework, our method not only significantly enhances medical image classification in practical settings but also innovates the application of entropy and information theory within deep learning and medical image processing realms. Extensive experiments demonstrate that DTTL achieves the best performance compared to existing state-of-the-art methods for imbalanced medical image classification tasks.