按年被提到
20162016 · 1 次2026
机器学习与深度学习›训练加速与低精度计算·arXiv:1601.06071 · cs.LG

Bitwise Neural Networks

Minje Kim, Paris Smaragdis · 2016
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2016-01-27 · 最近 2024-08-23
2不同的人
2活跃月份
2讨论串
166被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Based on the assumption that there exists a neural network that efficiently represents a set of Boolean functions between all binary inputs and outputs, we propose a process for developing and deploying neural networks whose weight parameters, bias terms, input, and intermediate hidden layer output signals, are all binary-valued, and require only basic bit logic for the feedforward pass. The proposed Bitwise Neural Network (BNN) is especially suitable for resource-constrained environments, since it replaces either floating or fixed-point arithmetic with significantly more efficient bitwise operations. Hence, the BNN requires for less spatial complexity, less memory bandwidth, and less power consumption in hardware. In order to design such networks, we propose to add a few training schemes, such as weight compression and noisy backpropagation, which result in a bitwise network that performs almost as well as its corresponding real-valued network. We test the proposed network on the MNIST dataset, represented using binary features, and show that BNNs result in competitive performance while offering dramatic computational savings.

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wrsh07 · 2024-08

“Because of the computational simplicity, I think there's a possibility that we will discover very cheap machine learning techniques that are discrete like this. I think this is novel (I've seen BNN https://arxiv.org/pdf/1601.06071 This actually makes things continuous for training, but if inference is sufficiently fast and you have an effective mechanism…”

What's Going on in Machine Learning? Some Minimal Models原评论 ↗
被提交为 story · 1 次