Internet publication icon

Internet publication

Minnorm training: an algorithm for training over-parameterized deep neural networks

Abstract:

In this work, we propose a new training method for finding minimum weight norm solutions in over-parameterized neural networks (NNs). This method seeks to improve training speed and generalization performance by framing NN training as a constrained optimization problem wherein the sum of the norm of the weights in each layer of the network is minimized, under the constraint of exactly fitting training data. It draws inspiration from support vector machines (SVMs), which are able to generalize...

Expand abstract
Publication status:
Published

Actions


Access Document


Files:

Authors


More by this author
Division:
MSD
Sub department:
Experimental Psychology
Role:
Author
ORCID:
0000-0002-9831-8812
Publication date:
2018-06-03
Language:
English
Keywords:
Pubs id:
1115537
Local pid:
pubs:1115537
Deposit date:
2020-07-02

Terms of use


Views and Downloads






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

TO TOP