In this paper, we propose DAC, Deep Autoencoder-based Clustering, a generalized data-driven framework to learn clustering representations using deep neuron networks. Experiment results show that our approach could effectively boost performance of the K-Means clustering algorithm on a variety types of ...
In this paper, we propose a multi-view clustering algorithm based on multiple auto-encoder, named MVC-MAE (see Fig.1). Specially, MVC-MAE first employs multiple auto-encoders to capture the nonlinear structure information in multi-view data and derive the low-dimensional representations of data...
Therefore, we cannot directly apply convolution, low-rank, or other methods to extract the image feature space based on the brain functional connection matrix. In the present study, inspired by deep auto-encoder network learning, we propose a deep multi-kernel auto-encoder clustering network (DMA...
Transform the data into more clustering-friendly representations: A deep version of k-means is based on learning a data representation and applying k-means in the embedded space. How to represent a cluster: a vector VS an autoencoder network. Data collapsing problem: 数据崩溃问题,对于每个数据库...
本文对应原文 Introduction~Taxonomy Of Deep Clustering(AE-based) Introduction 作者在本文中将深度聚类方法分为以下几类: 利用autoencoder得到可行的特征空间 基于前馈神经网络方法,且仅通过特定的loss函数进行训练,称为:CDNN 基于GAN的方法 基于VAE的方法
这篇博文主要是对论文“Deep Clustering by Gaussian Mixture Variational Autoencoders with Graph Embedding”的整理总结,这篇文章将图嵌入与概率深度高斯混合模型相结合,使网络学习到符合全局模型和局部结构约束的强大特征表示。将样本作为图上的节点,并最小化它们的后验分布之间的加权距离,在这里使用Jenson-Shannon散度...
K-AUTOENCODERS DEEP CLUSTERING(K-DAE,2020 IEEE) 技术标签: 读论文写在前面 这是一篇准备发表在IEEE上的文章(应该现在还没发表),2020.05已经发表在了ArXiv上了,是一篇关于深度聚类的文章,文章的思想很简单。 摘要 在这项研究中,我们提出了一种深度聚类算法,它是k-means算法的一种扩展。 每个聚类由自动编码器...
Fig. 4: Deep autoencoder (deepAE) representation clustering samples into cell types and diseases. a Significance score (−log10(p)) for first (green), second (blue), and third (violet) deepAE layers are more coherent (measured by a high Silhouette index (SI)) with respect to cell typ...
Image clustering is a complex procedure, which is significantly affected by the choice of image representation. Most of the existing image clustering methods treat representation learning and cluster...
By integrating autoencoders and the discovered low-dimensional embedding into the data-driven solver, the proposed framework is referred to as auto-embedding data-driven (AEDD) computing, which can also be considered as a hybrid of the NN-based constitutive modeling and the classical model-free ...