Conference item icon

Conference item

Trusting SVM for Piecewise Linear CNNs

Abstract:

We present a novel layerwise optimization algorithm for the learning objective of Piecewise-Linear Convolutional Neural Networks (PL-CNNs), a large class of convolutional neural networks. Specifically, PL-CNNs employ piecewise linear non-linearities such as the commonly used ReLU and max-pool, and an SVM classifier as the final layer. The key observation of our approach is that the problem corresponding to the parameter estimation of a layer can be formulated as a difference-of-convex (DC) pr...

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

Actions


Access Document


Files:

Authors


More by this author
Department:
Oxford, MPLS, Engineering Science
More by this author
Department:
Oxford, MPLS, Engineering Science
More by this author
Department:
Lady Margaret Hall
Acceptance date:
2017-02-06
Pubs id:
pubs:688986
URN:
uri:08f4a60f-b5f7-40a5-aff9-7ce4bce85b5b
UUID:
uuid:08f4a60f-b5f7-40a5-aff9-7ce4bce85b5b
Local pid:
pubs:688986

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