Deep learning method extracts medical knowledge from YouTube videos.
problem Improving healthcare information dissemination through machine learning.
method Developed a deep learning method to classify YouTube videos by medical knowledge level.
result Preliminary results show satisfactory performance in extracting medical knowledge from videos.
When devising a course of treatment for a patient, doctors often have little quantitative evidence on which to base their decisions, beyond their medical education and published clinical trials. Stanford Health Care alone has millions of electronic medical records (EMRs) that are only just recently being leveraged to i…
Observational studies are rising in importance due to the widespread accumulation of data in fields such as healthcare, education, employment and ecology. We consider the task of answering counterfactual questions such as, "Would this patient have lower blood sugar had she received a different medication?". We propose …
The paper integrates AI and expert knowledge to optimize radiotherapy decisions.
problem Optimizing radiation dose planning considering patient-specific information.
method Integrating Gaussian process models with deep neural networks to quantify uncertainty.
result Improves AI model performance and guides clinical decision making.
EduQG generates better educational questions by pre-training on scientific text.
problem Improving the quality of educational questions for scalable self-assessment.
method Adapting a large language model for educational question generation, pre-trained on scientific text.
result EduQG produces superior educational questions compared to baseline models.
AI could democratize education but risks inequality.
problem AI risks creating educational inequality.
method Speculation and posing questions on AI in education.
result AI could exacerbate educational inequality.
Educational game on crypto investment helps students grasp macroeconomics.
problem Weak connections between microeconomic decision-making and macroeconomic concepts in classroom games.
method Design and study of an educational game on cryptocurrency investment.
result Engages students in understanding macroeconomics through incentivized individual investment decisions.
TrueLearn uses Bayesian algorithms to match learners with educational resources.
problem Matching lifelong learners to open educational resources efficiently and effectively.
method TrueLearn uses a text ontology and Bayesian strategies to match learners with educational resources based on their background knowledge and material novelty.
result TrueLearn algorithms show promise in building an effective educational recommendation system.
Personalized education at scale improves student outcomes.
problem Traditional personalized education is expensive and inequitable.
method Adapting educational presentations using RL, semi-supervised learning, NLP, and CV.
result Personalized education at scale can improve student outcomes.
PREREQ learns concept prerequisites from online educational resources.
problem Inferring prerequisite relations between educational concepts.
method PREREQ uses latent representations of concepts from Pairwise Latent Dirichlet Allocation and a Siamese neural network to learn from course prerequisites and labeled data.
result PREREQ outperforms state-of-the-art approaches and can learn from less data.
Paper aims to improve education online in South Africa using NMT for Setswana.
problem Inclusion of machine translation for low-resourced local languages in online education.
method Demonstrates state-of-the-art performance on English-to-Setswana translation using the Transformer architecture.
result Current NMT techniques show promise for African languages, beating previous methods by 5.33 BLEU points.
EduGym simplifies reinforcement learning education for students.
problem Students struggle to translate between equations and code in reinforcement learning.
method EduGym provides educational environments and interactive notebooks.
result 86% of students and researchers find EduGym useful for education.
Co-adaptation is a special form of on-line learning where an algorithm A must assist an unknown algorithm B to perform some task. This is a general framework and has applications in recommendation systems, search, education, and much more. Today, the most common use of co-adaptive algorithms is …
TrueLearn Python library for personalized educational recommendations.
problem Building educational recommendation systems with humanly-intuitive user representations.
method Online learning Bayesian models and open learner concept.
result Library includes models and representations for user control and interpretability.
In this paper the correlation between education, research and macroeconomic strength of countries at a global scale is analyzed on the basis of statistical data published by the UNIDO and OECD. It uses sets of composite indicators describing the economical performance and competitiveness as well as those relevant for h…
Study analyzes online student behavior patterns using log data.
problem Understanding and optimizing student learning in online educational systems.
method Non-negative matrix factorization techniques for soft clustering.
result Behavioral changes of individual students and the system over time.
Study forecasts COVID-19 cases in Iran using deep learning.
problem Predicting the spread of COVID-19 in Iran.
method Deep learning models (Prophet, LSTM, AR, ARIMA) for forecasting.
result Deep learning models outperform time series forecasting.
Neural pedagogical agent updates user models in real-time for mobile education apps.
problem Real-time user modeling for dynamic mobile education platforms.
method Bidirectional recurrent neural networks with attention mechanism over embedded question-response pairs.
result Model outperforms existing approaches in predicting user response correctness.
Improves content allocation in educational platforms with sparse data.
problem Imbalanced content allocation and delayed convergence in adaptive strategies.
method Introduces WAPTS, an algorithm that refines Thompson Sampling for data-sparse environments.
result Demonstrates earlier and more reliable identification of promising treatments.
Bayesian model identifies skill difficulties and student subgroups in engineering education.
problem Identifying and supporting diverse student needs in entry-level university engineering modules.
method Hierarchical Bayesian modeling of student response data.
result Clear patterns of skill mastery and distinct student subgroups identified.
Builds a novel educational recommender for lifelong learners.
problem Challenges in creating scalable and transparent models for lifelong learning.
method Integrative approach combining content novelty, background knowledge, and learner engagement.
result TrueLearn achieves promising performance while retaining a human interpretable learner model.
Hidden Markov Model predicts student performance in educational games.
problem Estimating student knowledge progression in educational games.
method Time series analysis using hidden Markov model with game features.
result State trajectories accurately predict student performance.
Paper classifies brain signals using eigenvalues for 2D and 3D educational content questions.
problem Classifying brain signals for 2D and 3D educational content questions.
method Eigenvalues of covariance matrix used as features; KNN and SVM classifiers applied.
result No significant difference in learning, memory retention, and recall between 2D and 3D educational content.
Paper tackles zero-shot code feedback using rubric sampling with deep learning.
problem Lack of historical data for supervised learning in introductory programming assignments.
method Human-in-the-loop rubric sampling with deep learning inference.
result Autonomous feedback for first students is more accurate than data-hungry algorithms and approaches human level fidelity.
Educational site for AI training at INSA Toulouse.
problem Adapting AI training to job market needs.
method Basic math, statistical learning, self-training tutorials, game.
result Students trained in self-training and practical AI.
Model predicts higher education dropout risk with interpretable parameters.
problem Predicting and understanding student dropout risk in higher education.
method Sparse interpretable post-clustering logistic regression.
result Model identifies distinct dropout risk subgroups within the student population.
Semantic TrueLearn uses semantic graphs to improve educational recommendation systems.
problem Challenges in handling semantic and hierarchical structure in knowledge areas.
method Introduces a novel learner model that exploits semantic relatedness between knowledge components using a Wikipedia link graph.
result Achieves statistically significant improvements in predictive performance for educational engagement.
This paper ranks Latin American countries based on AI potential.
problem Identifying emerging AI powers in Latin America.
method Ranking based on infrastructure, education, and finance.
result Argentina, Colombia, Uruguay, Costa Rica, and Ecuador are new emerging powers in AI.
A new framework for playing and learning board games.
problem Tackling the tedious and repetitive aspects of coding for board game AI.
method Developed a generic TD(λ)-n-tuple agent for arbitrary board games. result TD(λ)-n-tuple outperforms other generic agents on various games. AR app visualizes Quranic Surah al-Fil for Islamic education.
problem Lack of interactive and context-rich learning materials for Quranic studies.
method Research and development approach, including data collection, user requirement analysis, interface design, 3D asset creation, and integration of AR technology.
result AR application achieved high accuracy and user satisfaction, enhancing learner engagement and understanding.
Each year, roughly 30% of first-year students at US baccalaureate institutions do not return for their second year and over $9 billion is spent educating these students. Yet, little quantitative research has analyzed the causes and possible remedies for student attrition. Here, we describe initial efforts to model stud…
We revisit a recently introduced agent model[ACS {\bf 11}, 99 (2008)], where economic growth is a consequence of education (human capital formation) and innovation, and investigate the influence of the agents' social network, both on an agent's decision to pursue education and on the output of new ideas. Regular and ra…
Study reveals hierarchical structure of global geo-industrial clusters using labor flow network.
problem Identifying and analyzing the hierarchical structure of geo-industrial clusters globally.
method Constructed a labor flow network from LinkedIn data and applied recursive network community detection.
result Geo-industrial clusters defined by labor flow show stronger association with financial performance.
The gender wage gap varies significantly among women based on socio-economic characteristics.
problem Understanding the extent of gender inequality in earnings among U.S. women.
method High-dimensional wage regression and double lasso analysis of 2016 American Community Survey data.
result The gender wage gap varied substantially across women and was driven by marital status, having children, race, occupation, industry, and educational attainment.
Study improves engagement prediction in educational videos.
problem Addressing cold-start problem in educational recommenders.
method Introduced VLE dataset with content and engagement features, conducted experiments.
result VLE dataset leads to better engagement prediction models.
A new system recommends educational content based on student and peer interests.
problem Recommending suitable educational content for students.
method Neural Educational Recommendation Engine (NERE) using a recurrent neural network.
result NERE achieves higher recall and R^2 scores than traditional methods.
AR app enhances young children's understanding of Wudhu.
problem Teaching Wudhu to young children is challenging.
method Needs analysis, system design, implementation, testing (Black Box Testing).
result AR technology improves children's learning interest and understanding of Wudhu.
Bayesian active learning improves holistic educational assessments.
problem Gap between holistic CJ and criterion-based rubrics in education.
method Extends Bayesian CJ to handle multiple LO components, using entropy-based active learning.
result Enhanced predictive rankings with uncertainty estimates and quantified assessor agreement.
Study improves statistical power for detecting algorithmic bias in educational data.
problem Challenges in measuring algorithmic bias using ABROCA due to skewed distribution.
method Investigates ABROCA's distributional properties and proposes nonparametric randomization tests.
result ABROCA-based bias assessments are underpowered in typical EDM sample sizes.
New methods for evaluating and optimizing policies in offline RL with unobserved confounders.
problem Evaluating and optimizing policies in the presence of unobserved confounders.
method Characterized settings and algorithms for consistent value estimates and lower bounds, with sample complexity guarantees.
result Proved local convergence guarantees for offline policy improvement.
Proposes TLRNet for estimating treatment effects from observational data.
problem Estimating individual treatment effects from observational data.
method Deep neural network with pseudo-single learner structure.
result Acceptable results obtained using one estimator for two treatment groups.
Teaches reproducible research to medical students and postgrads.
problem Lack of reproducibility in medical research practices.
method Designed and delivered a lecture series on reproducible research.
result Encountered practical obstacles in reproducing a published analysis.
Develops a fair post-processing method for student success predictions.
problem Ensuring fairness in predictive student models for educational applications.
method Uses the MADD metric to improve model fairness while maintaining accuracy.
result Successfully improved fairness of predictive models for student success.
NeuralCD diagnoses student proficiency in exercises using neural networks.
problem Capturing complex student-exercise interactions for accurate cognitive diagnosis.
method Proposes NeuralCD framework using neural networks to learn complex interactions between students and exercises, incorporating monotonicity for interpretability.
result Demonstrates effectiveness of NeuralCD framework on real-world datasets, achieving both accuracy and interpretability.
Bayesian approach selects subsets of variables for interpretable prediction and identifies key factors in educational outcomes.
problem Challenges in subset selection for stability, regularization, and inference.
method Bayesian perspective on subset selection, deriving optimal subsets and variable importance metrics.
result Better prediction, interval estimation, and variable selection compared to competing methods.
Improved forecasting of suicide attempts using LSGPs for patients with little data.
problem Challenges in predicting suicide attempts due to their rarity and patient heterogeneity.
method Introduced Latent Similarity Gaussian Processes (LSGPs) to capture patient heterogeneity.
result LSGPs outperform baseline models, even without kernel-design, and offer new insights into patient similarity.
Interactive tools help teach economics online.
problem Teaching macroeconomic models online.
method Browser-based simulation toolkits.
result Intuitive approach to comparative statics.
Efficiently fine-tunes patient-independent seizure detection models with tensor kernel machine.
problem Improving seizure detection accuracy for wearable devices.
method Transfer learning with tensor kernel machine using canonical polyadic decomposition.
result Patient fine-tuned model achieves high performance with smaller model size.