Papers › Training deep neural networks with low precision multiplications

Training deep neural networks with low precision multiplications

22 Dec 2014arXiv:1412.7024archive 2025-07-28

Matthieu Courbariaux, Yoshua Bengio, Jean-Pierre David

Multipliers are the most space and power-hungry arithmetic operators of the digital implementation of deep neural networks. We train a set of state-of-the-art neural networks (Maxout networks) on three benchmark datasets: MNIST, CIFAR-10 and SVHN. They are trained with three distinct formats: floating point, fixed point and dynamic fixed point. For each of those datasets and for each of those formats, we assess the impact of the precision of the multiplications on the final error after training. We find that very low precision is sufficient not just for running trained networks but also for training them. For example, it is possible to train Maxout networks with 10 bits multiplications.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

MatthieuCourbariaux/deep-learning-multipliers officialmentioned in papermentioned on GitHubGPL-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Maxout

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections