Deep Unsupervised Clustering Using Mixture of Autoencoders
dc.contributor.author | Zhang, Dejiao | |
dc.contributor.author | Sun, Yifan | |
dc.contributor.author | Eriksson, Brian | |
dc.contributor.author | Balzano, Laura | |
dc.date.accessioned | 2018-08-10T20:23:13Z | |
dc.date.available | 2018-08-10T20:23:13Z | |
dc.date.issued | 2017-12-26 | |
dc.identifier.uri | https://hdl.handle.net/2027.42/145190 | |
dc.description.abstract | Unsupervised clustering is one of the most fundamental challenges in machine learning. A popular hypothesis is that data are generated from a union of low-dimensional nonlinear manifolds; thus an approach to clustering is identifying and separating these manifolds. In this paper, we present a novel approach to solve this problem by using a mixture of autoencoders. Our model consists of two parts: 1) a collection of autoencoders where each autoencoder learns the underlying manifold of a group of similar objects, and 2) a mixture assignment neural network, which takes the concatenated latent vectors from the autoencoders as input and infers the distribution over clusters. By jointly optimizing the two parts, we simultaneously assign data to clusters and learn the underlying manifolds of each cluster. | en_US |
dc.description.sponsorship | Part of this work was done when Dejiao Zhang was doing an internship at Technicolor Research. Both Dejiao Zhang and Laura Balzano’s participations were funded by DARPA-16-43-D3M-FP-037. Both Yifan Sun and Brian Eriksson's participation occurred while also at Technicolor Research. | en_US |
dc.language.iso | en_US | en_US |
dc.subject | machine learning, deep learning, autoencoder, clustering | en_US |
dc.title | Deep Unsupervised Clustering Using Mixture of Autoencoders | en_US |
dc.type | Technical Report | en_US |
dc.subject.hlbsecondlevel | Electrical Engineering | |
dc.subject.hlbsecondlevel | Computer Science | |
dc.subject.hlbtoplevel | Engineering | |
dc.contributor.affiliationother | Technicolor | en_US |
dc.contributor.affiliationother | Adobe | en_US |
dc.contributor.affiliationumcampus | Ann Arbor | en_US |
dc.description.bitstreamurl | https://deepblue.lib.umich.edu/bitstream/2027.42/145190/1/mixae_arxiv_submit.pdf | |
dc.identifier.orcid | https://orcid.org/0000-0003-2914-123X | en_US |
dc.description.filedescription | Description of mixae_arxiv_submit.pdf : Main tech report | |
dc.identifier.name-orcid | Balzano, Laura; 0000-0003-2914-123X | en_US |
dc.owningcollname | Electrical Engineering and Computer Science, Department of (EECS) |
Files in this item
Remediation of Harmful Language
The University of Michigan Library aims to describe library materials in a way that respects the people and communities who create, use, and are represented in our collections. Report harmful or offensive language in catalog records, finding aids, or elsewhere in our collections anonymously through our metadata feedback form. More information at Remediation of Harmful Language.
Accessibility
If you are unable to use this file in its current format, please select the Contact Us link and we can modify it to make it more accessible to you.