Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • 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
The preimage of rectifier network activities
KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP. (Computer Vision)ORCID iD: 0000-0001-5211-6388
Show others and affiliations
2017 (English)Conference paper, Poster (with or without abstract) (Refereed)
Abstract [en]

We give a procedure for explicitly computing the complete preimage of activities of a layer in a rectifier network with fully connected layers, from knowledge of the weights in the network. The most general characterisation of preimages is as piecewise linear manifolds in the input space with possibly multiple branches. This work therefore complements previous demonstrations of preimages obtained by heuristic optimisation and regularization algorithms Mahendran & Vedaldi (2015; 2016) We are presently empirically evaluating the procedure and it’s ability to extract complete preimages as well as the general structure of preimage manifolds.

Place, publisher, year, edition, pages
2017.
Keyword [en]
Understanding, Deep Learning, Rectifier Networks, Preimage, Inverting Deep Networks
National Category
Computer Vision and Robotics (Autonomous Systems)
Research subject
Computer Science; Mathematics
Identifiers
URN: urn:nbn:se:kth:diva-206976OAI: oai:DiVA.org:kth-206976DiVA: diva2:1094831
Conference
International Conference on Learning Representations
Note

QC 20170511

Available from: 2017-05-11 Created: 2017-05-11 Last updated: 2017-05-11Bibliographically approved

Open Access in DiVA

No full text

Search in DiVA

By author/editor
Azizpour, Hossein
By organisation
Computer Vision and Active Perception, CVAP
Computer Vision and Robotics (Autonomous Systems)

Search outside of DiVA

GoogleGoogle Scholar

Total: 107 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • 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