-
Notifications
You must be signed in to change notification settings - Fork 7
Description
论文信息
标题: Pseudo-Invertible Neural Networks
作者: Yamit Ehrlich, Nimrod Berman, Assaf Shocher
发布时间: 2026-02-05
分类: cs.LG
PDF: Download
简介
The Moore-Penrose Pseudo-inverse (PInv) serves as the fundamental solution for linear systems. In this paper, we propose a natural generalization of PInv to the nonlinear regime in general and to neural networks in particular. We introduce Surjective Pseudo-invertible Neural Networks (SPNN), a class of architectures explicitly designed to admit a tractable non-linear PInv. The proposed non-linear PInv and its implementation in SPNN satisfy fundamental geometric properties. One such property is null-space projection or "Back-Projection",
推荐理由
论文1可深入讨论:非线性伪逆的数学严格性、Back-Projection在语义控制中的应用潜力、与现有扩散先验的兼容性
讨论
请对这篇论文发表您的见解:
- 论文的创新点是什么?
- 方法是否合理?
- 实验结果是否可信?
- 有哪些可以改进的地方?
由 arXiv Monitor 自动创建