BriefGPT.xyz
Jun, 2023
PMaF:基于深度声明式层的主部特征
PMaF: Deep Declarative Layers for Principal Matrix Features
HTML
PDF
Zhiwei Xu, Hao Wang, Yanbin Liu, Stephen Gould
TL;DR
利用可微分的深度声明层,即最小二乘球(LESS)和隐式特征分解(IED),学习主要的矩阵特征(PMaF),将数据特征表示为包含来自高维矩阵的主导信息的低维向量。
Abstract
We explore two
differentiable deep declarative layers
, namely
least squares on sphere
(LESS) and
implicit eigen decomposition
(IED), for l
→