pith. sign in

arxiv: 1502.02478 · v1 · pith:KLEEUVXKnew · submitted 2015-02-09 · 💻 cs.NE · cs.CV

Efficient batchwise dropout training using submatrices

classification 💻 cs.NE cs.CV
keywords dropoutbatchwiseminibatchnetworksmaskneuralpatternsample
0
0 comments X
read the original abstract

Dropout is a popular technique for regularizing artificial neural networks. Dropout networks are generally trained by minibatch gradient descent with a dropout mask turning off some of the units---a different pattern of dropout is applied to every sample in the minibatch. We explore a very simple alternative to the dropout mask. Instead of masking dropped out units by setting them to zero, we perform matrix multiplication using a submatrix of the weight matrix---unneeded hidden units are never calculated. Performing dropout batchwise, so that one pattern of dropout is used for each sample in a minibatch, we can substantially reduce training times. Batchwise dropout can be used with fully-connected and convolutional neural networks.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.