Machine learning models do not improve prediction of academic risk in a large Australian dataset.
problem Improving prediction of academic risk using machine learning.
method Applied popular machine learning models to a large dataset of Australian students.
result Machine learning models do not outperform logistic regression for detecting students at risk of poor performance.
Study examines dependence of extreme electricity prices in Australian markets.
problem Understanding and managing risks of extreme price outcomes in Australian electricity markets.
method Examined extremal dependence using extremograms for 5-minute and 30-minute price data.
result Persistence and dependence of extreme prices are influenced by market structure and renewable energy share.
Predictive models of training load data failed to accurately predict injuries in Australian football.
problem Predicting injuries in Australian football using training load data.
method Training load data from GPS, accelerometers, and player ratings were analyzed using various predictive models.
result The best model for hamstring injuries had an AUC of 0.76, but overall predictive performance was poor.
We present four methods of assessing the diversification potential within a stock market, two of these are based on principal component analysis. They were applied to the Australian stock exchange for the years 2000 to 2014 and all show a consistent picture. The potential for diversification declined almost monotonical…
Study shows foreign institutional investment increases liquidity commonality in large Australian stocks.
problem Impact of foreign institutional investment on liquidity commonality in Australian stocks.
method Cross-sectional and time-series analysis of Australian equity market data.
result Foreign institutional investment contributes to increased exposure of large stocks to unexpected liquidity events.
Changes in Australian Age Pension mean-tests affect retirement planning and benefits.
problem Policy changes impact optimal retirement decisions and benefits.
method Optimal stochastic control problem in a utility maximizing lifecycle model.
result New rules decrease benefits from means-testing but increase housing allocation slightly.
Deep learning framework predicts streamflow and flood probabilities in Australian catchments.
problem Large-scale flooding prediction challenges due to model calibration and missing data.
method Ensemble quantile-based deep learning framework using quantile regression and CAMELS dataset.
result Notable efficacy and uncertainties in streamflow forecasts with varied catchment properties.
DeepWeeds dataset aids in robust weed species classification for rangeland robotics.
problem Robust classification of weed species in rangeland environments.
method Development of a large multiclass image dataset and application of deep learning models.
result Inception-v3 and ResNet-50 achieved 95.1% and 95.7% classification accuracy, respectively.
Modeling retirement behavior with public pension, optimal consumption and housing decisions.
problem Retirement behavior, consumption, housing, investment, and public pension effects.
method Expected utility model, stochastic control problem, maximum likelihood method.
result Optimal housing, consumption, and risky asset allocation depend on age and wealth, sensitive to means-tested Age Pension.
Paper introduces a new IV regression method for mixed-frequency data.
problem Estimating high-dimensional slope parameters in mixed-frequency data.
method Tikhonov-regularized estimator for high-dimensional linear IV regression.
result High-dimensional slope parameter can be accurately estimated using a low-frequency instrumental variable.
High-value transactions between Australian banks are settled in the Reserve Bank Information and Transfer System (RITS) administered by the Reserve Bank of Australia. RITS operates on a real-time gross settlement (RTGS) basis and settles payments sourced from the SWIFT, the Austraclear, and the interbank transactions e…
The Basel II internal ratings-based (IRB) approach to capital adequacy for credit risk plays an important role in protecting the Australian banking sector against insolvency. We outline the mathematical foundations of regulatory capital for credit risk, and extend the model specification of the IRB approach to a more g…
Two open problems in Sasaki geometry are discussed.
problem Open problems in Sasaki geometry.
method Discussion and description of open problems.
result Two open problems in Sasaki geometry are identified.
The study uses Hidden Markov Models to analyze student enrollment patterns and academic performance.
problem Limited understanding of how enrollment patterns affect academic performance.
method Applied Hidden Markov Models to categorize enrollment strategies and compare academic outcomes.
result Mixed enrollment strategies lead to better academic performance, especially during part-time semesters.
Predicts student dropout using transcript data.
problem Student attrition in higher education.
method Machine learning model using transcript data.
result Dropout can be accurately predicted from a single term of transcript data.
This paper improves student networks to be more robust against perturbations.
problem Improving robustness of lightweight student networks.
method The paper introduces a method to make student networks more confident and robust by leveraging teacher networks.
result The proposed method enhances the robustness of student networks without sacrificing accuracy.
Developed predictive models for improving programming course performance.
problem Improving student performance in programming courses.
method Used M5P Decision Tree and Linear Regression Classifier on structured questionnaire data.
result Variable-based LRC model produced the best model with least evaluation metrics.
Predicts student performance in interactive online question pools using GNNs.
problem Predicting student performance in interactive online question pools with evolving knowledge.
method Proposes R^2GCN, a GNN model for heterogeneous networks to predict student performance.
result Achieves higher accuracy in student performance prediction than traditional methods.
Proposes RaT to mitigate bias in student-teacher estimation.
problem Systematic bias in teacher's predictions propagates to student model.
method Uses teacher to estimate residuals in student's predictions.
result RaT method reduces teacher bias effect and achieves optimal rate.
Paper proposes a fast stability scanning method for future grid scenarios.
problem Capturing inter-seasonal variations in renewable generation.
method Novel feature selection algorithm and self-adaptive PSO-k-means clustering.
result Reduced computational burden up to ten times with acceptable accuracy.
Analyzed writing style changes in Danish high school students.
problem Detecting global development trends and identifying at-risk students in high school writing.
method Used a Siamese neural network to compute essay similarity and clustered student profiles.
result High school students' writing styles become less similar as they progress, with some students showing significant improvement and others limited development or setbacks.
Enhances student diversity in collaborative learning.
problem Student homogenization in large groups.
method Random routing, diverse feature sets, and random subgroup imitation.
result Significantly outperforms state-of-the-art approaches.
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.
The paper proposes a framework to detect student misconceptions from textual responses.
problem Detecting misconceptions from students' responses to open-response questions.
method A natural language processing-based probabilistic model for detecting common misconceptions.
result The proposed framework excels at classifying and detecting common misconceptions.
Student-teacher learning improves generalization with noisy inputs.
problem Transfer knowledge from clean inputs to noisy inputs.
method Analyzes student-teacher learning using deep linear networks and experiments with nonlinear networks.
result Three factors are vital for success: zero training loss, teacher knowledge, and feature decomposition.
The Open University studies student online behavior in virtual learning environments.
problem Improving retention rates in online modules.
method GUHA and Markov chain-based analysis of student activity.
result Both methods are valid for modeling student activities.
Predicts student outcomes in real-time using domain adaptation.
problem Real-time student performance prediction in online courses.
method GritNet architecture with unsupervised domain adaptation.
result GritNet enhances real-time predictions, especially in early weeks.
A new teacher-class network method compresses DNNs by distributing knowledge to multiple student networks.
problem Overwhelming size of Deep Neural Networks (DNNs).
method Single teacher with multiple student networks, transferring knowledge to each student.
result The combined knowledge of the class of students achieves better performance and reduces parameters.
GritNet predicts student performance using deep learning.
problem Predicting student performance in online coursework.
method GritNet is a deep learning algorithm based on bidirectional long short term memory (BLSTM).
result GritNet outperforms logistic regression and improves predictions in the early stages of a course.
Real-time student performance prediction without historical data.
problem Predict student performance in real-time with limited historical data.
method Domain adaptation framework using GritNet architecture with unsupervised transfer learning.
result GritNet generalizes well across different courses and enhances predictions in the early stages.
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.
Enhanced Bayesian optimization using Student-t processes for multi-objective problems.
problem Optimizing multiple objectives in complex problems.
method Developed an analytical hypervolume-based probability of improvement for Student-t processes.
result Effective in optimizing difficult multi-objective problems.
Improved ImageNet classification with semi-supervised learning.
problem Image classification with limited labeled data.
method Noisy Student Training: semi-supervised learning with noisy student models.
result 88.4% top-1 accuracy on ImageNet, 2.0% better than state-of-the-art.
Detects student engagement states using unobtrusive appearance, context, and mouse data.
problem Detecting student engagement states in a classroom setting.
method Multimodal approach combining appearance, context, and mouse data; classifiers are fused at the decision level.
result Effective detection of student engagement states in a classroom setting.
Student's-T processes improve on Gaussian processes by handling outliers and variance more flexibly.
problem Outliers and variance limitations in Gaussian processes.
method Generalization of Gaussian processes using Student's-T distribution, with new kernel function and update rule.
result Student's-T processes provide better performance in Bayesian optimization, especially with outliers.
Modeling student behaviors and multiple predictions for early intervention.
problem Predicting student outcomes and interactions among multiple tasks.
method Proposes a variant of LSTM and soft-attention mechanism for heterogeneous behaviors, and co-attention mechanism for task interactions.
result Demonstrated effectiveness in predicting student outcomes and interactions.
Proposes KTAN for better training of student networks with both intermediate representations and probability distributions.
problem Reduces large computation and storage cost of deep networks by transferring generalization ability.
method Holistically considers intermediate representations and probability distributions; uses a Teacher-to-Student layer and adversarial learning.
result Significantly improves performance of student networks on image classification and object detection tasks.
Estimates model performance from compute budget for distillation.
problem Risk mitigation in large-scale distillation.
method Distillation scaling law based on compute budget allocation.
result Maximizes student performance with compute-optimal allocation.
Distilled models often fail to match teacher models, despite improving generalization.
problem The discrepancy between teacher and student predictive distributions remains large.
method Investigated the optimization difficulties and dataset details affecting student performance.
result Optimizing for matching the teacher does not always lead to better generalization.
A new method for student-initiated action advice using novelty detection.
problem Exploration and sample inefficiency in RL, especially with teacher absence.
method Random Network Distillation (RND) to measure advice novelty, updates only for advised states.
result Significant performance improvement over state-of-the-art methods, especially in challenging scenarios.
Study examines how different assessment formats affect student learning in a data communications course.
problem Understanding how various assessment formats impact student learning outcomes.
method Comparing student learning outcomes across multiple assessment formats in a core data communications course at George Mason University.
result Collective assessment formats enhance student knowledge demonstration.
Deep learning model predicts wildfire spread in Australia.
problem Predicting the full distribution of wildfire spread in Australia.
method Graph convolutional neural networks and extended generalized Pareto distribution.
result Efficacy of the model demonstrated through hazard assessment.
Paper defines new time series equivalence and distances for bushfire analysis.
problem Analyzing structural similarity in time series data during natural disasters.
method Introduces algebraic equivalence relations and Lp distances between time series. result Demonstrates the existence of metrizable topologies on time series equivalence classes.
Improved image reconstruction using VAEs with Student's t-prior.
problem Improving the robustness of VAEs in image reconstruction.
method Proposed a VAE with Student's t-distribution as prior, trained all distribution parameters.
result Better image reconstruction achieved with Student's t-prior compared to Gaussian priors.
Explains Cartan geometries for graduate students.
problem None explicitly stated, focuses on definition.
method Definition and explanation.
result Defines Cartan geometries for a specific audience.
Study predicts academic achievement using students' support networks.
problem Predicting academic achievement in college students.
method Decision tree and random forest algorithms applied to Ties data.
result Different types of support are important for different demographics and genders.
Self-training with noisy student-teacher boosts keyword spotting accuracy.
problem Robust keyword spotting in challenging conditions.
method Aggressive data augmentation and self-training with noisy student-teacher approach.
result Significant accuracy improvement in difficult conditions, up to 60%.
This paper proposes a method to embed teacher knowledge into a student network without increasing parameters.
problem The need for portable neural networks on mobile devices with limited resources.
method Feature embedding approach to distill knowledge from a teacher network to a student network without introducing new parameters.
result The proposed method maintains the performance of the teacher network while significantly reducing computational and storage complexity.