C&EN

A Simple and Scalable Kernel Density Approach for Reliable Uncertainty Quantification in Atomistic Machine Learning

Creative Commons (CC): This is a Creative Commons license. Attribution (BY): Credit must be given to the creator.
IEEE

LowGradQ: Adaptive Gradient Quantization for Low-Bit CNN Training via Kernel Density Estimation-Guided Thresholding and Hardware-Efficient Stochastic Rounding Unit

Abstract: This paper proposes a hardware-efficient INT8 training framework with dual-scale adaptive gradient quantization (DAGQ) to cope with the growing need for efficient on-device CNN training.
Frontiers

Stroke rate–stroke length dynamics in elite freestyle swimming: application of kernel density estimation

Objectives: To analyse stroke rate (SR) and stroke length (SL) combinations among elite swimmers to better understand stroke strategies across all race distances of freestyle events. Design: We ...
IEEE

A Statistical Analysis Method for Electromagnetic Sensitivity Effects Based on Kernel Density Estimation and Gaussian Copula Model

Abstract: This paper introduces a statistical analysis method for electromagnetic sensitivity based on kernel density estimation and Gaussian Copula modeling. We address a critical limitation in ...