Related papers: A rapid evaluation of Australia's COVID-era appren…
Demand for technology focused STEM professionals will increase globally over the coming decade, with many countries finding it difficult to meet growing demand. Compounding this are difficulties in attracting and retaining female…
Artificial intelligence (AI) applications to support human tutoring have potential to significantly improve learning outcomes, but engagement issues persist, especially among students from low-income backgrounds. We introduce an AI-assisted…
The COVID-19 pandemic has brought significant and enduring shifts in various aspects of life, including increased flexibility in work arrangements. In a longitudinal study, spanning 24 months with six measurement points from April 2020 to…
We have previously described the reformed introductory physics course, Collaborative Learning through Active Sense-Making in Physics (CLASP), for bioscience students at a large public research one university (Original University) and…
Incomplete take-up of welfare benefits remains a major policy puzzle. This paper decomposes the causes of incomplete welfare take-up into two mechanisms: inattention, where households do not consider program participation, and active…
At large research universities in the USA, introductory physics labs are often run by graduate student teaching assistants (TAs). Thus, efforts to reform introductory labs should address the need for effective and relevant TA professional…
This paper proposes a novel Bayesian active learning method for Bayesian model updating, which is termed as "Streamlined Bayesian Active Learning Cubature" (SBALC). The core idea is to approximate the log-likelihood function using Gaussian…
In this paper, we consider a novel variant of the multi-armed bandit (MAB) problem, MAB with cost subsidy, which models many real-life applications where the learning agent has to pay to select an arm and is concerned about optimizing…
Measures of disengagement provide insights into unproductive use of learning opportunities. Although measures of active disengagement, such as gaming the system and mind-wandering, are well studied, loss of practice time due to outright…
Programming assistants powered by large language models have improved dramatically, yet existing benchmarks still evaluate them in narrow code-generation settings. Recent efforts such as InfiBench and StackEval rely on Stack Overflow…
We investigate the impact of artificial intelligence (AI) adoption on skill requirements using 14 million online job vacancies from Chinese listed firms (2018-2022). Employing a novel Extreme Multi-Label Classification (XMLC) algorithm…
Computer-aided design (CAD) programs are essential to engineering as they allow for better designs through low-cost iterations. While CAD programs are typically taught to undergraduate students as a job skill, such software can also help…
Adaptive bitrate (ABR) algorithms are used to adapt the video bitrate based on the network conditions to improve the overall video quality of experience (QoE). Recently, reinforcement learning (RL) and asynchronous advantage actor-critic…
A well-known failure mode of neural networks is that they may confidently return erroneous predictions. Such unsafe behaviour is particularly frequent when the use case slightly differs from the training context, and/or in the presence of…
Capture-the-Flag (CTF) competitions serve as gateways into offensive cybersecurity, yet they often present steep barriers for novices due to complex toolchains and opaque workflows. Recently, agentic AI frameworks for cybersecurity promise…
Class imbalance poses a major challenge for machine learning as most supervised learning models might exhibit bias towards the majority class and under-perform in the minority class. Cost-sensitive learning tackles this problem by treating…
Progression and assessment rules are often treated as administrative details, yet they fundamentally shape who is allowed to remain in higher education, and on what terms. This article uses a calibrated agent-based model to examine how…
Scoring models support decision-making in financial institutions. Their estimation and evaluation are based on the data of previously accepted applicants with known repayment behavior. This creates sampling bias: the available labeled data…
In reinforcement learning, a decision needs to be made at some point as to whether it is worthwhile to carry on with the learning process or to terminate it. In many such situations, stochastic elements are often present which govern the…
Well-known for its simplicity and effectiveness in classification, AdaBoost, however, suffers from overfitting when class-conditional distributions have significant overlap. Moreover, it is very sensitive to noise that appears in the…