arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2212.12899math.NAcs.AIcs.LGcs.NA
收藏

FMM-Net:基于快速多极子方法的神经网络结构

FMM-Net: neural network architecture based on the Fast Multipole Method

Skolkovo Institute of Science and Technology(斯科尔科沃科技学院);Marchuk Institute of Numerical Mathematics of the Russian Academy of Sciences(俄罗斯科学院马尔丘克数值数学研究所)

Daria Sushnikova, Pavel Kharyuk, Ivan Oseledets

摘要:

在本文中,我们提出了一种新的神经网络结构的基础上的H2矩阵。尽管具有H2启发架构的网络已经存在,但我们的方法旨在通过考虑H2矩阵的稀疏模板来降低内存成本并提高性能。在与其他神经网络(包括已知的基于H2的神经网络)的数值比较中,我们的架构在性能、内存和可扩展性方面表现出了优势。

英文摘要:

In this paper, we propose a new neural network architecture based on the H2 matrix. Even though networks with H2-inspired architecture already exist, and our approach is designed to reduce memory costs and improve performance by taking into account the sparsity template of the H2 matrix. In numerical comparison with alternative neural networks, including the known H2-based ones, our architecture showed itself as beneficial in terms of performance, memory, and scalability.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑