BriefGPT.xyz
Sep, 2019
深度资产化聚类
Deep Amortized Clustering
HTML
PDF
Juho Lee, Yoonho Lee, Yee Whye Teh
TL;DR
本文介绍了一种深度摊销聚类（DAC）神经网络架构，通过少量正向传递学习高效聚类数据集，摊销聚类通过元学习，不需要手工先验知识即可聚类数据点和计算数据集中集群的数量。在合成和图像数据上的实验结果表明，DAC可以高效、准确地聚类来自与训练集相同分布的新数据集。
Abstract
We propose a
deep amortized clustering
(DAC), a
neural architecture
which learns to cluster datasets efficiently using a few forward passes. DAC implicitly learns what makes a cluster, how to group data points in
→