Maximum entropy methods for extracting the learned features of deep neural networks

Alex Finnegan; Jun S. Song

doi:10.1371/journal.pcbi.1005836

Loading metrics

Open Access

Peer-reviewed

Research Article

Maximum entropy methods for extracting the learned features of deep neural networks

Alex Finnegan,

Roles Conceptualization, Data curation, Formal analysis, Investigation, Methodology, Software, Validation, Writing – original draft, Writing – review & editing

Affiliations Department of Physics, University of Illinois, Urbana-Champaign, Urbana, Illinois, United States of America, Carl R. Woese Institute for Genomic Biology, University of Illinois, Urbana-Champaign, Urbana, Illinois, United States of America
⨯
Jun S. Song

Roles Conceptualization, Funding acquisition, Methodology, Supervision, Writing – review & editing

* E-mail: songj@illinois.edu

Affiliations Department of Physics, University of Illinois, Urbana-Champaign, Urbana, Illinois, United States of America, Carl R. Woese Institute for Genomic Biology, University of Illinois, Urbana-Champaign, Urbana, Illinois, United States of America

http://orcid.org/0000-0002-0422-2175

⨯

Maximum entropy methods for extracting the learned features of deep neural networks

Alex Finnegan,
Jun S. Song

Published: October 30, 2017
https://doi.org/10.1371/journal.pcbi.1005836
See the preprint

About the Authors

Alex Finnegan

Roles Conceptualization, Data curation, Formal analysis, Investigation, Methodology, Software, Validation, Writing – original draft, Writing – review & editing

Affiliations Department of Physics, University of Illinois, Urbana-Champaign, Urbana, Illinois, United States of America, Carl R. Woese Institute for Genomic Biology, University of Illinois, Urbana-Champaign, Urbana, Illinois, United States of America

Jun S. Song

Roles Conceptualization, Funding acquisition, Methodology, Supervision, Writing – review & editing

* E-mail: songj@illinois.edu

http://orcid.org/0000-0002-0422-2175

Competing Interests

The authors have declared that no competing interests exist.

Subject Areas
?

For more information about PLOS Subject Areas, click here.
We want your feedback. Do these Subject Areas make sense for this article? Click the target next to the incorrect Subject Area and let us know. Thanks for your help!

Nucleotide sequencing
Is the Subject Area "Nucleotide sequencing" applicable to this article?

Thanks for your feedback.
Network motifs
Is the Subject Area "Network motifs" applicable to this article?

Thanks for your feedback.
Sequence motif analysis
Is the Subject Area "Sequence motif analysis" applicable to this article?

Thanks for your feedback.
Nucleotide mapping
Is the Subject Area "Nucleotide mapping" applicable to this article?

Thanks for your feedback.
Nucleosome mapping
Is the Subject Area "Nucleosome mapping" applicable to this article?

Thanks for your feedback.
Genomics
Is the Subject Area "Genomics" applicable to this article?

Thanks for your feedback.
Nucleotides
Is the Subject Area "Nucleotides" applicable to this article?

Thanks for your feedback.
Machine learning
Is the Subject Area "Machine learning" applicable to this article?

Thanks for your feedback.