IEEE

Deep Networks as Denoising Algorithms: Sample-Efficient Learning of Diffusion Models in High-Dimensional Graphical Models

Abstract: We investigate the efficiency of deep neural networks for approximating scoring functions in diffusion-based generative modeling. While existing approximation theories leverage the ...
IEEE

Understanding Error Propagation in Deep-Learning Neural Networks’ Accelerators and Applications

Abstract: Editor’s notes: This article reviews some of the first experiments on deep neural networks to analyze the propagation of soft errors from hardware to the ...
C&EN

Deep Learning-Enabled Unbiased Precision Toxicity Assessment of Zebrafish Organ Development

School of Energy and Environment, State Key Laboratory of Marine Environmental Health, City University of Hong Kong, Kowloon, Hong Kong, China Research Centre for the Oceans and Human Health, City ...