BriefGPT.xyz
Jul, 2018
关于狭窄深度神经网络的决策区域
On decision regions of narrow deep neural networks
HTML
PDF
Hans-Peter Beise, Steve Dias Da Cruz, Udo Schröder
TL;DR
研究发现，当神经网络的宽度小于或等于输入维度时，决策区域的所有联通组件都是无界的。本文还对此进行了数值实验，并补充了最近对这种狭窄神经网络逼近能力和决策区域连通性的研究成果。
Abstract
We show that for
neural network
functions that have width less or equal to the input dimension all connected components of
decision regions
are unbounded. The result holds for continuous and strictly monotonic ac
→