BriefGPT.xyz
Feb, 2019
基于深度分歧的聚类方法
Deep Divergence-Based Approach to Clustering
HTML
PDF
Michael Kampffmeyer, Sigurd Løkse, Filippo M. Bianchi, Lorenzo Livi, Arnt-Børre Salberg...
TL;DR
我们提出了一种新的深度聚类网络，利用信息理论差异度量的鉴别能力，提出了一种新颖的损失函数，避免了聚类分区的退化结构。
Abstract
A promising direction in
deep learning
research consists in learning
representations
and simultaneously discovering
cluster structure
in u
→