Lazy Evaluation of Convolutional Filters

05/27/2016

∙

by   Sam Leroux, et al.

∙

0

∙

share

In this paper we propose a technique which avoids the evaluation of certain convolutional filters in a deep neural network. This allows to trade-off the accuracy of a deep neural network with the computational and memory requirements. This is especially important on a constrained device unable to hold all the weights of the network in memory.