papers AI Learner
The Github is limit! Click to go to the new site.

Low-memory convolutional neural networks through incremental depth-first processing

2018-04-28
Jonathan Binas, Yoshua Bengio

Abstract

We introduce an incremental processing scheme for convolutional neural network (CNN) inference, targeted at embedded applications with limited memory budgets. Instead of processing layers one by one, individual input pixels are propagated through all parts of the network they can influence under the given structural constraints. This depth-first updating scheme comes with hard bounds on the memory footprint: the memory required is constant in the case of 1D input and proportional to the square root of the input dimension in the case of 2D input.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1804.10727

PDF

https://arxiv.org/pdf/1804.10727


Similar Posts

Comments