Natural and Social Sciences (IPAS) learning in elementary schools requires contextual conceptual understanding; however, student achievement remains low due to passive instructional practices that fail to accommodate diverse learning styles. This study aimed to determine the effect of the quantum teaching learning mode...
Yeni Madina Matondang, Antonius Remigius Abi, Lasmaria Agnes Sinaga· LEARNING Jurnal Inovasi Pene...· 0 citations
The Frontier Index is a continuously updated, evidence-scored index of the latest scientific discoveries and breakthroughs in science and technology. Each entry carries a transparent Frontier Score from 0 to 100, composed of three pillars (evidence, impact, and novelty), computed from up to 13 independent public data s...
Frontier· Zenodo (CERN European Organi...· 0 citations
Peer review is a scholarly and professional duty for which every researcher bears direct responsibility. This responsibility stems from the fact that the scientific development of any field, along with the enhancement of its journals and scholarly resources, is profoundly influenced by the quality of its peer review pr...
We propose a spectral-based, unsupervised representation learning framework to derive low-dimensional embeddings for clinical concepts and patients in rare disease cohorts from electronic health records, where data are high-dimensional but sample sizes are limited. To overcome this challenge, we incorporate a knowledge...
Feiqing Huang, Zongqi Xia, Rong Ma et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
We study online conformal prediction in a partially observed panel: a new cross-section of peer outcomes is observed before each target outcome, target feedback may be intermittent or absent, and neither units nor rounds need be exchangeable. We propose Weighted Temporal Quantile Adjustment (W-TQA), which combines simi...
Autocorrelation is a common property of time-series, where each observation is dependent on its predecessors. In deep time-series forecasting, it raises two central challenges: (1) designing backbone architectures to model autocorrelation in history sequences, and (2) devising loss functions to model autocorrelation in...
Hao Wang, Licheng Pan, Qingsong Wen et al.· 0 citations
Models with intractable normalizing constants are widely used in statistics and machine learning. Assessing the adequacy of such models poses significant challenges: obtaining samples from the fitted model often requires sophisticated sampling algorithms. Moreover, model fitting sometimes requires iterative numerical o...
A growing class of machine-learning objects -- covariance and Gram matrices, kernel and attention matrices, MIMO channel matrices, density operators -- are naturally spectra rather than coordinate vectors. Building a denoising diffusion model for such data by corrupting eigenvalues coordinatewise is not merely elegant:...
In many real-world applications, ensuring the robustness and stability of deep neural networks (DNNs) is crucial, particularly for image classification tasks that encounter various input perturbations. While Mixup-based data augmentation techniques have been widely adopted to enhance the resilience of trained models ag...
Jiaming Hu, Yeping Jin, Debarghya Mukherjee et al.· 0 citations
The identifiability analysis of linear Ordinary Differential Equation (ODE) systems is a necessary prerequisite for making reliable causal inferences about these systems. While identifiability has been well studied in scenarios where the system is fully observable, the conditions for identifiability remain unexplored w...
Yuanyuan Wang, Biwei Huang, Wei Huang et al.· 0 citations
Graph neural networks (GNNs) are routinely employed for spatiotemporal forecasting, yet their performance across widely used benchmark datasets is inconsistent. Here, we perform an audit of dataset properties and baseline models to assess the quality of the benchmarks, and the robustness of the conclusions drawn from t...
Kenneth Martin, Simon Heilig, Asja Fischer et al.· 0 citations
Bayesian filtering of partially and noisily observed dynamical systems seeks to infer the evolving conditional distribution of the state of a dynamical system given observations, in an online fashion. This Bayesian filtering distribution is rarely available as a supervised learning target. However, one can often use th...
Eviatar Bach, Ricardo Baptista, Jochen Br\"ocker et al.· 0 citations
Jennifer Neville did not want to go into computer science—but that’s exactly where she landed. Neville discusses the starts and stops that led to her professional sweet spot and her work identifying “surprising failures” making it hard for AI to handle complexity. The post What AI gets wrong and what failure teaches us appeared first on Microsoft Research.
