⌘+K

Pulse Explore Communities Researchers Journals

Home Communities Explore

January 1, 2017Journal of Machine Learning Research

Quantized neural networks

HubaraItay CourbariauxMatthieu SoudryDaniel El-YanivRan BengioYoshua

View at Publisher

Ask AI

Bookmark

Share

Abstract

We introduce a method to train Quantized Neural Networks (QNNs) -- neural networks with extremely low precision (e.g., 1-bit) weights and activations, at run-time. At traintime the quantized weight...

Discussion

No takes yet. Share an insight, caveat, or question.

Cite This Study

HubaraItay et al. (2017) studied this question.

synapsesocial.com/papers/69d9533a9402b8412aa3cf6e https://doi.org/10.5555/3122009.3242044

View at Publisher

Ask AI

Bookmark

Share

Keep reading

Synapse has enriched 5 related papers. Consider them for comparative context:

1Adaptive Online Prediction by Following the Perturbed Leader.Journal of Machine Learning Research · Thu,
2MEKA: A multi-label/multi-target extension to WekaJournal of Machine Learning Research · Fri,
3River: Machine learning for streaming data in pythonJournal of Machine Learning Research · Tue,
4An Introduction to Artificial Prediction Markets for ClassificationJournal of Machine Learning Research · Mon,
5Pattern Recognition for Conditionally Independent DataJournal of Machine Learning Research · Thu,

More from Journal of Machine Learning Research

Marginal Likelihood Integrals for Mixtures of Independence ModelsWed,
Undercomplete Blind Subspace DeconvolutionWed,
Nonlinear Models Using Dirichlet Process MixturesWed,
Matrix Completion from Noisy EntriesTue,
Manifold Learning: The Price of NormalizationTue,