BriefGPT.xyz
Mar, 2018
深度连续聚类
Deep Continuous Clustering
HTML
PDF
Sohil Atul Shah, Vladlen Koltun
TL;DR
通过深度自编码器实现非线性降维和聚类，优化作为聚类过程的自编码器，避免之前聚类算法中离散目标的缺陷，无需先验知识即可进行聚类，实验证明该算法优于状态的聚类方案并具有普适性。
Abstract
clustering
high-dimensional datasets
is hard because interpoint distances become less informative in high-dimensional spaces. We present a
cluste
→