Conference item icon

Conference item

Deep CNN sparse coding analysis: Towards average case

Abstract:

Deep convolutional sparse coding (D-CSC) is a framework reminiscent of deep convolutional neural nets (DCNN), but by omitting the learning of the dictionaries one can more transparently analyse the role of the activation function and its ability to recover activation paths through the layers. Papyan, Romano, and Elad conducted an analysis of such an architecture [1], showed the relationship with DCNNs, and proved conditions under which a D-CSC is guaranteed to recover activation paths. A tech...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed
Version:
Accepted manuscript

Actions


Access Document


Files:
Publisher copy:
10.1109/DSW.2018.8439894

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Mathematical Institute
Oxford college:
Exeter College
Publisher:
Institute of Electrical and Electronics Publisher's website
Publication date:
2018-08-20
Acceptance date:
2018-04-26
DOI:
Pubs id:
pubs:846459
URN:
uri:6028ac4c-a330-43d1-961e-df1fe4527ef9
UUID:
uuid:6028ac4c-a330-43d1-961e-df1fe4527ef9
Local pid:
pubs:846459
ISBN:
9781538644119

Terms of use


Metrics



If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP