按年被提到
20142015 · 1 次2026
机器学习与深度学习›训练加速与低精度计算·arXiv:1412.7024 · cs.LG

Training deep neural networks with low precision multiplications

Matthieu Courbariaux, Yoshua Bengio, Jean-Pierre David · 2014
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2015-05-09 · 最近 2016-09-15
2不同的人
2活跃月份
2讨论串
407被引(OpenAlex)
arXiv 摘要(候选层不写导读)

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.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论benanne · 2015-05

“Indeed, 64 bits of accuracy is overkill for a lot of ML algorithms, where there is so much noise that the additional quantization noise due to low precision is negligible. Most deep neural nets are already being trained in single precision because that is what NVIDIA GPUs can do the fastest. There has been quite some research on reducing the bit depth fur…”

Fast Approximate Logarithms, Part I: The Basics原评论 ↗
评论Houshalter · 2016-09

“Backpropagation can work with any precision, as long as you use stochastic rounding (so that the rounding errors are not correlated.) Without stochastic rounding even 16 bits will have rounding error bias. http://arxiv.org/abs/1412.7024”

A TensorFlow Implementation of DeepMind's WaveNet Paper原评论 ↗