Zobrazeno 1 - 10
of 314
pro vyhledávání: '"Yu, Zhongjie"'
$\chi$SPN: Characteristic Interventional Sum-Product Networks for Causal Inference in Hybrid Domains
Autor:
Poonia, Harsh, Willig, Moritz, Yu, Zhongjie, Zečević, Matej, Kersting, Kristian, Dhami, Devendra Singh
Causal inference in hybrid domains, characterized by a mixture of discrete and continuous variables, presents a formidable challenge. We take a step towards this direction and propose Characteristic Interventional Sum-Product Network ($\chi$SPN) that
Externí odkaz:
http://arxiv.org/abs/2408.07545
In many real-world scenarios, it is crucial to be able to reliably and efficiently reason under uncertainty while capturing complex relationships in data. Probabilistic circuits (PCs), a prominent family of tractable probabilistic models, offer a rem
Externí odkaz:
http://arxiv.org/abs/2312.07790
Few-shot audio classification is an emerging topic that attracts more and more attention from the research community. Most existing work ignores the specificity of the form of the audio spectrogram and focuses largely on the embedding space borrowed
Externí odkaz:
http://arxiv.org/abs/2302.14204
Probabilistic circuits (PCs) are models that allow exact and tractable probabilistic inference. In contrast to neural networks, they are often assumed to be well-calibrated and robust to out-of-distribution (OOD) data. In this paper, we show that PCs
Externí odkaz:
http://arxiv.org/abs/2302.06544
Autor:
Sun, Di, Liao, Tengyang, Lin, Hongyong, Sang, Yaoyao, Liu, Yu, Ma, Qingbao, Yu, Zhongjie, Zhang, Bin, Jiang, Wei
Publikováno v:
In Food Chemistry 30 October 2024 456
Autor:
Luo, Qing, Yang, Huiyang, Lv, Bodong, Luo, Xiaohua, Chen, Changcai, Zhong, Rui, Yu, Zhongjie, Wang, Sujuan, Gao, Fei, Fang, Chunsheng, Ren, Weijun, Ma, Shengcan
Publikováno v:
In Intermetallics October 2024 173
Autor:
Zhao, Fan, Jiang, Lijun, Wang, Chenyu, Li, Shuangdie, Sun, Di, Ma, Qingbao, Yu, Zhongjie, Liu, Yu, Jiang, Wei
Publikováno v:
In Industrial Crops & Products 1 September 2024 215
Probabilistic circuits (PCs) have become the de-facto standard for learning and inference in probabilistic modeling. We introduce Sum-Product-Attention Networks (SPAN), a new generative model that integrates probabilistic circuits with Transformers.
Externí odkaz:
http://arxiv.org/abs/2109.06587
Autor:
Cai, Haotian, Tao, Lei, Zhou, Xianyuan, Liu, Yu, Sun, Di, Ma, Qingbao, Yu, Zhongjie, Jiang, Wei
Publikováno v:
In Journal of Agriculture and Food Research June 2024 16
Publikováno v:
In International Journal of Gastronomy and Food Science June 2024 36