Zobrazeno 1 - 4
of 4
pro vyhledávání: '"FANG Peng"'
We present a rigorous theoretical analysis of the convergence rate of the deep mixed residual method (MIM) when applied to a linear elliptic equation with various types of boundary conditions. The MIM method has been proposed as a more effective nume
Externí odkaz:
http://arxiv.org/abs/2305.06193
Autor:
Fang, Peng, Khan, Arijit, Luo, Siqiang, Wang, Fang, Feng, Dan, Li, Zhenli, Yin, Wei, Cao, Yuchao
Publikováno v:
49th International Conference on Very Large Data Bases (VLDB 2023), Vancouver, Canada - August 28 to September 1, 2023
Graph embedding maps graph nodes to low-dimensional vectors, and is widely adopted in machine learning tasks. The increasing availability of billion-edge graphs underscores the importance of learning efficient and effective embeddings on large graphs
Externí odkaz:
http://arxiv.org/abs/2303.15702
Detected the steerability bounds of the generalized Werner states via BackPropagation neural network
Autor:
Zhang, Jun, He, Kan, Zhang, Ying, Hao, Yu-Yang, Hou, Jin-Chuan, Lan, Fang-Peng, Niu, Bao-Ning
We use error BackPropagation (BP) neural network to determine whether an arbitrary two-qubit quantum state is steerable and optimize the steerability bounds of the generalized Werner state. The results show that no matter how we choose the features f
Externí odkaz:
http://arxiv.org/abs/2110.13379
In this paper, we propose multi-band MelGAN, a much faster waveform generation model targeting to high-quality text-to-speech. Specifically, we improve the original MelGAN by the following aspects. First, we increase the receptive field of the genera
Externí odkaz:
http://arxiv.org/abs/2005.05106