Výsledky vyhledávání

Report

Leveraging Local Structure for Improving Model Explanations: An Information Propagation Approach

Autor: Yang, Ruo, Wang, Binghui, Bilgic, Mustafa

Numerous explanation methods have been recently developed to interpret the decisions made by deep neural network (DNN) models. For image classifiers, these methods typically provide an attribution score to each pixel in the image to quantify its cont

Externí odkaz: http://arxiv.org/abs/2409.16429

Zobrazit plný text záznamu

Report

IDGI: A Framework to Eliminate Explanation Noise from Integrated Gradients

Autor: Yang, Ruo, Wang, Binghui, Bilgic, Mustafa

Integrated Gradients (IG) as well as its variants are well-known techniques for interpreting the decisions of deep neural networks. While IG-based approaches attain state-of-the-art performance, they often integrate noise into their explanation salie

Externí odkaz: http://arxiv.org/abs/2303.14242

Zobrazit plný text záznamu

Report

High-throughput optical absorption spectra for inorganic semiconductors

Autor: Yang, Ruo Xi, Horton, Matthew K., Munro, Jason, Persson, Kristin A.

An optical absorption spectrum constitutes one of the most fundamental material characteristics, with relevant applications ranging from material identification to energy harvesting and optoelectronics. However, the database of both experimental and

Externí odkaz: http://arxiv.org/abs/2209.02918

Zobrazit plný text záznamu