This website requires JavaScript.

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

Daria SushnikovaPavel KharyukIvan Oseledets
Dec 2022
摘要
In this paper, we propose a new neural network architecture based on the H2matrix. Even though networks with H2-inspired architecture already exist, andour approach is designed to reduce memory costs and improve performance bytaking into account the sparsity template of the H2 matrix. In numericalcomparison with alternative neural networks, including the known H2-based ones,our architecture showed itself as beneficial in terms of performance, memory,and scalability.
展开全部
图表提取

暂无人提供速读十问回答

论文十问由沈向洋博士提出,鼓励大家带着这十个问题去阅读论文,用有用的信息构建认知模型。写出自己的十问回答,还有机会在当前页面展示哦。

Q1论文试图解决什么问题?
Q2这是否是一个新的问题?
Q3这篇文章要验证一个什么科学假设?
0
被引用
笔记
问答