Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Learning Representations with a Dynamic Objective Sparse Autoencoder
Örebro University, School of Science and Technology. (AASS)ORCID iD: 0000-0002-0579-7181
Örebro University, School of Science and Technology. (AASS)ORCID iD: 0000-0002-3122-693X
2012 (English)Conference paper, Poster (with or without abstract) (Refereed)
Abstract [en]

The main objective of an auto-encoder is to reconstruct the input signals via a feature representation of latent variables. The number of latent variables defines the representational capacity limit of the model. For data sets where some or all signals contain noise there is an unnecessary amount of capacity spent on trying to reconstruct these signals. One solution is to increase the number of hidden units to increase the capacity so that there will be enough capacity to capture the valuable information. Another solution is to pre-process the signals or perform a manual signal selection. In this paper, we propose a method that will dynamically change the objective function depending on the current performance of the model. This is done by weighting the objective function individually for each input unit in order to guide the feature leaning and decrease the influence that problematic signals have on the learning of features. We evaluate our method on various multidimensional time-series data sets and handwritten digit recognition data sets and compare our results with a standard sparse auto-encoder.

Place, publisher, year, edition, pages
2012.
National Category
Computer Science
Research subject
Computer Science
Identifiers
URN: urn:nbn:se:oru:diva-34599OAI: oai:DiVA.org:oru-34599DiVA: diva2:710528
Conference
Neural Information Processing Systems
Available from: 2014-04-07 Created: 2014-04-07 Last updated: 2017-10-17Bibliographically approved

Open Access in DiVA

dosae(852 kB)321 downloads
File information
File name FULLTEXT01.pdfFile size 852 kBChecksum SHA-512
c41d24a7f68b4caa7dd62eb91daebae78f1ecd5e7c543b0926d1dd7ee232688cd9d6db9e05a2587848734447fced146d1bdb95df570882f3ccee5fc10adae21d
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Längkvist, MartinLoutfi, Amy
By organisation
School of Science and Technology
Computer Science

Search outside of DiVA

GoogleGoogle Scholar
Total: 321 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 596 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf