Výsledky vyhledávání - "Luo, Yuxiang"

Report

On Gorenstein homological dimension of groups

Autor: Luo, Yuxiang, Ren, Wei

Let $G$ be a group and $R$ be a ring. We define the Gorenstein homological dimension of $G$ over $R$, denoted by ${\rm Ghd}_{R}G$, as the Gorenstein flat dimension of trivial $RG$-module $R$. It is proved that ${\rm Ghd}_SG \leq {\rm Ghd}_RG$ for any

Externí odkaz: http://arxiv.org/abs/2205.15542

Zobrazit plný text záznamu

Dissertation/ Thesis

Explaining Automated Decisions in Practice : Insights from the Swedish Credit Scoring Industry

Autor: Matz, Filip, Luo, Yuxiang

The field of explainable artificial intelligence (XAI) has gained momentum in recent years following the increased use of AI systems across industries leading to bias, discrimination, and data security concerns. Several conceptual frameworks for how

Externí odkaz: http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-300897

Zobrazit plný text záznamu

Report

GLOW : Global Weighted Self-Attention Network for Web Search

Autor: Shan, Xuan, Liu, Chuanjie, Xia, Yiqian, Chen, Qi, Zhang, Yusi, Ding, Kaize, Liang, Yaobo, Luo, Angen, Luo, Yuxiang

Deep matching models aim to facilitate search engines retrieving more relevant documents by mapping queries and documents into semantic vectors in the first-stage retrieval. When leveraging BERT as the deep matching model, the attention score across

Externí odkaz: http://arxiv.org/abs/2007.05186

Zobrazit plný text záznamu

Report

MIRA: Leveraging Multi-Intention Co-click Information in Web-scale Document Retrieval using Deep Neural Networks

Autor: Zhang, Yusi, Liu, Chuanjie, Luo, Angen, Xue, Hui, Shan, Xuan, Luo, Yuxiang, Xia, Yiqian, Yan, Yuanchi, Wang, Haidong

We study the problem of deep recall model in industrial web search, which is, given a user query, retrieve hundreds of most relevance documents from billions of candidates. The common framework is to train two encoding models based on neural embeddin

Externí odkaz: http://arxiv.org/abs/2007.01510

Zobrazit plný text záznamu

Report

ACOUSTIC-TURF: Acoustic-based Privacy-Preserving COVID-19 Contact Tracing

Autor: Luo, Yuxiang, Zhang, Cheng, Zhang, Yunqi, Zuo, Chaoshun, Xuan, Dong, Lin, Zhiqiang, Champion, Adam C., Shroff, Ness

In this paper, we propose a new privacy-preserving, automated contact tracing system, ACOUSTIC-TURF, to fight COVID-19 using acoustic signals sent from ubiquitous mobile devices. At a high level, ACOUSTIC-TURF adaptively broadcasts inaudible ultrason

Externí odkaz: http://arxiv.org/abs/2006.13362

Zobrazit plný text záznamu