Pith. sign in

REVIEW

Dropout Rademacher Complexity of Deep Neural Networks

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1402.3811 v2 pith:AFU4FRKA submitted 2014-02-16 cs.NE stat.ML

classification cs.NEstat.ML
keywords networksneuralcomplexitydeepdropoutrademacherbeenmany
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Great successes of deep neural networks have been witnessed in various real applications. Many algorithmic and implementation techniques have been developed, however, theoretical understanding of many aspects of deep neural networks is far from clear. A particular interesting issue is the usefulness of dropout, which was motivated from the intuition of preventing complex co-adaptation of feature detectors. In this paper, we study the Rademacher complexity of different types of dropout, and our theoretical results disclose that for shallow neural networks (with one or none hidden layer) dropout is able to reduce the Rademacher complexity in polynomial, whereas for deep neural networks it can amazingly lead to an exponential reduction of the Rademacher complexity.

Discussion (0). Sign in to comment.

Pith tools