Although the use of technologies like multimedia and virtual reality (VR) in training offer the promise of improved learning, these richer and potentially more engaging materials do not consistently produce superior learning outcomes. Default approaches to such training may inadvertently mimic concepts like naive realism in display design, and desirable difficulties in the science of learning - fostering an impression of greater learning dissociated from actual gains in memory. This research examined the influence of format of instructions in learning to assemble items from components. Participants in two experiments were trained on the steps to assemble a series of bars, that resembled Meccano pieces, into eight different shapes. After training on pairs of shapes, participants rated the likelihood they would remember the shapes and then were administered a recognition test. Relative to viewing a static diagram, viewing videos of shapes being constructed in a VR environment (Experiment 1) or viewing within an immersive VR system (Experiment 2) elevated participants' assessments of their learning but without enhancing learning outcomes. Overall, these findings illustrate how future workers might mistakenly come to believe that technologically advanced support improves learning and prefer instructional designs that integrate similarly complex cues into training.
相關內容
Relying on human experts to evaluate CEFR speaking assessments in an e-learning environment creates scalability challenges, as it limits how quickly and widely assessments can be conducted. We aim to automate the evaluation of CEFR B2 English speaking assessments in e-learning environments from conversation transcripts. First, we evaluate the capability of leading open source and commercial Large Language Models (LLMs) to score a candidate's performance across various criteria in the CEFR B2 speaking exam in both global and India-specific contexts. Next, we create a new expert-validated, CEFR-aligned synthetic conversational dataset with transcripts that are rated at different assessment scores. In addition, new instruction-tuned datasets are developed from the English Vocabulary Profile (up to CEFR B2 level) and the CEFR-SP WikiAuto datasets. Finally, using these new datasets, we perform parameter efficient instruction tuning of Mistral Instruct 7B v0.2 to develop a family of models called EvalYaks. Four models in this family are for assessing the four sections of the CEFR B2 speaking exam, one for identifying the CEFR level of vocabulary and generating level-specific vocabulary, and another for detecting the CEFR level of text and generating level-specific text. EvalYaks achieved an average acceptable accuracy of 96%, a degree of variation of 0.35 levels, and performed 3 times better than the next best model. This demonstrates that a 7B parameter LLM instruction tuned with high-quality CEFR-aligned assessment data can effectively evaluate and score CEFR B2 English speaking assessments, offering a promising solution for scalable, automated language proficiency evaluation.
Supervised operator learning centers on the use of training data, in the form of input-output pairs, to estimate maps between infinite-dimensional spaces. It is emerging as a powerful tool to complement traditional scientific computing, which may often be framed in terms of operators mapping between spaces of functions. Building on the classical random features methodology for scalar regression, this paper introduces the function-valued random features method. This leads to a supervised operator learning architecture that is practical for nonlinear problems yet is structured enough to facilitate efficient training through the optimization of a convex, quadratic cost. Due to the quadratic structure, the trained model is equipped with convergence guarantees and error and complexity bounds, properties that are not readily available for most other operator learning architectures. At its core, the proposed approach builds a linear combination of random operators. This turns out to be a low-rank approximation of an operator-valued kernel ridge regression algorithm, and hence the method also has strong connections to Gaussian process regression. The paper designs function-valued random features that are tailored to the structure of two nonlinear operator learning benchmark problems arising from parametric partial differential equations. Numerical results demonstrate the scalability, discretization invariance, and transferability of the function-valued random features method.
Distributed learning offers a practical solution for the integrative analysis of multi-source datasets, especially under privacy or communication constraints. However, addressing prospective distributional heterogeneity and ensuring communication efficiency pose significant challenges on distributed statistical analysis. In this article, we focus on integrative estimation of distributed heterogeneous precision matrices, a crucial task related to joint precision matrix estimation where computation-efficient algorithms and statistical optimality theories are still underdeveloped. To tackle these challenges, we introduce a novel HEterogeneity-adjusted Aggregating and Thresholding (HEAT) approach for distributed integrative estimation. HEAT is designed to be both communication- and computation-efficient, and we demonstrate its statistical optimality by establishing the convergence rates and the corresponding minimax lower bounds under various integrative losses. To enhance the optimality of HEAT, we further propose an iterative HEAT (IteHEAT) approach. By iteratively refining the higher-order errors of HEAT estimators through multi-round communications, IteHEAT achieves geometric contraction rates of convergence. Extensive simulations and real data applications validate the numerical performance of HEAT and IteHEAT methods.
The rise of machine learning (ML) and its embedding in systems has drastically changed the engineering of software-intensive systems. Traditionally, software engineering focuses on manually created artifacts such as source code and the process of creating them, as well as best practices for integrating them, i.e., software architectures. In contrast, the development of ML artifacts, i.e. ML models, comes from data science and focuses on the ML models and their training data. However, to deliver value to end users, these ML models must be embedded in traditional software, often forming complex topologies. In fact, ML-enabled software can easily incorporate many different ML models. While the challenges and practices of building ML-enabled systems have been studied to some extent, beyond isolated examples, little is known about the characteristics of real-world ML-enabled systems. Properly embedding ML models in systems so that they can be easily maintained or reused is far from trivial. We need to improve our empirical understanding of such systems, which we address by presenting the first large-scale study of real ML-enabled software systems, covering over 2,928 open source systems on GitHub. We classified and analyzed them to determine their characteristics, as well as their practices for reusing ML models and related code, and the architecture of these systems. Our findings provide practitioners and researchers with insight into practices for embedding and integrating ML models, bringing data science and software engineering closer together.
Neural Ordinary Differential Equations (ODEs) represent a significant advancement at the intersection of machine learning and dynamical systems, offering a continuous-time analog to discrete neural networks. Despite their promise, deploying neural ODEs in practical applications often encounters the challenge of stiffness, a condition where rapid variations in some components of the solution demand prohibitively small time steps for explicit solvers. This work addresses the stiffness issue when employing neural ODEs for model order reduction by introducing a suitable reparametrization in time. The considered map is data-driven and it is induced by the adaptive time-stepping of an implicit solver on a reference solution. We show the map produces a nonstiff system that can be cheaply solved with an explicit time integration scheme. The original, stiff, time dynamic is recovered by means of a map learnt by a neural network that connects the state space to the time reparametrization. We validate our method through extensive experiments, demonstrating improvements in efficiency for the neural ODE inference while maintaining robustness and accuracy. The neural network model also showcases good generalization properties for times beyond the training data.
With the recent advancements in machine learning (ML), numerous ML-based approaches have been extensively applied in software analytics tasks to streamline software development and maintenance processes. Nevertheless, studies indicate that despite their potential usefulness, ML models are vulnerable to adversarial attacks, which may result in significant monetary losses in these processes. As a result, the ML models' robustness against adversarial attacks must be assessed before they are deployed in software analytics tasks. Despite several techniques being available for adversarial attacks in software analytics tasks, exploring adversarial attacks using ML explainability is largely unexplored. Therefore, this study aims to investigate the relationship between ML explainability and adversarial attacks to measure the robustness of ML models in software analytics tasks. In addition, unlike most existing attacks that directly perturb input-space, our attack approach focuses on perturbing feature-space. Our extensive experiments, involving six datasets, three ML explainability techniques, and seven ML models, demonstrate that ML explainability can be used to conduct successful adversarial attacks on ML models in software analytics tasks. This is achieved by modifying only the top 1-3 important features identified by ML explainability techniques. Consequently, the ML models under attack fail to accurately predict up to 86.6% of instances that were correctly predicted before adversarial attacks, indicating the models' low robustness against such attacks. Finally, our proposed technique demonstrates promising results compared to four state-of-the-art adversarial attack techniques targeting tabular data.
Analyzing human motion is an active research area, with various applications. In this work, we focus on human motion analysis in the context of physical rehabilitation using a robot coach system. Computer-aided assessment of physical rehabilitation entails evaluation of patient performance in completing prescribed rehabilitation exercises, based on processing movement data captured with a sensory system, such as RGB and RGB-D cameras. As 2D and 3D human pose estimation from RGB images had made impressive improvements, we aim to compare the assessment of physical rehabilitation exercises using movement data obtained from both RGB-D camera (Microsoft Kinect) and estimation from RGB videos (OpenPose and BlazePose algorithms). A Gaussian Mixture Model (GMM) is employed from position (and orientation) features, with performance metrics defined based on the log-likelihood values from GMM. The evaluation is performed on a medical database of clinical patients carrying out low back-pain rehabilitation exercises, previously coached by robot Poppy.
Automated Machine Learning (AutoML) significantly simplifies the deployment of machine learning models by automating tasks from data preprocessing to model selection to ensembling. AutoML systems for tabular data often employ post hoc ensembling, where multiple models are combined to improve predictive accuracy. This typically results in longer inference times, a major limitation in practical deployments. Addressing this, we introduce a hardware-aware ensemble selection approach that integrates inference time into post hoc ensembling. By leveraging an existing framework for ensemble selection with quality diversity optimization, our method evaluates ensemble candidates for their predictive accuracy and hardware efficiency. This dual focus allows for a balanced consideration of accuracy and operational efficiency. Thus, our approach enables practitioners to choose from a Pareto front of accurate and efficient ensembles. Our evaluation using 83 classification datasets shows that our approach sustains competitive accuracy and can significantly improve ensembles' operational efficiency. The results of this study provide a foundation for extending these principles to additional hardware constraints, setting the stage for the development of more resource-efficient AutoML systems.
Auditing the use of data in training machine-learning (ML) models is an increasingly pressing challenge, as myriad ML practitioners routinely leverage the effort of content creators to train models without their permission. In this paper, we propose a general method to audit an ML model for the use of a data-owner's data in training, without prior knowledge of the ML task for which the data might be used. Our method leverages any existing black-box membership inference method, together with a sequential hypothesis test of our own design, to detect data use with a quantifiable, tunable false-detection rate. We show the effectiveness of our proposed framework by applying it to audit data use in two types of ML models, namely image classifiers and foundation models.
We address the task of automatically scoring the competency of candidates based on textual features, from the automatic speech recognition (ASR) transcriptions in the asynchronous video job interview (AVI). The key challenge is how to construct the dependency relation between questions and answers, and conduct the semantic level interaction for each question-answer (QA) pair. However, most of the recent studies in AVI focus on how to represent questions and answers better, but ignore the dependency information and interaction between them, which is critical for QA evaluation. In this work, we propose a Hierarchical Reasoning Graph Neural Network (HRGNN) for the automatic assessment of question-answer pairs. Specifically, we construct a sentence-level relational graph neural network to capture the dependency information of sentences in or between the question and the answer. Based on these graphs, we employ a semantic-level reasoning graph attention network to model the interaction states of the current QA session. Finally, we propose a gated recurrent unit encoder to represent the temporal question-answer pairs for the final prediction. Empirical results conducted on CHNAT (a real-world dataset) validate that our proposed model significantly outperforms text-matching based benchmark models. Ablation studies and experimental results with 10 random seeds also show the effectiveness and stability of our models.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191