MétaCan
← all works

Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations

2016· preprint· en· 1,425 citations· W2524428287 on OpenAlex· 10.48550/arxiv.1609.07061

Why is this work in the frame?

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

Canadian affiliationAn author listed a Canadian institution. This is the only route the usual frame has.

Machine scores (provisional)

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Opus teacher head0.055
GPT teacher head0.195
Teacher spread
0.140 · how far apart the two teachers sit on this one work
Validation status
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

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 train-time the quantized weights and activations are used for computing the parameter gradients. During the forward pass, QNNs drastically reduce memory size and accesses, and replace most arithmetic operations with bit-wise operations. As a result, power consumption is expected to be drastically reduced. We trained QNNs over the MNIST, CIFAR-10, SVHN and ImageNet datasets. The resulting QNNs achieve prediction accuracy comparable to their 32-bit counterparts. For example, our quantized version of AlexNet with 1-bit weights and 2-bit activations achieves $51\%$ top-1 accuracy. Moreover, we quantize the parameter gradients to 6-bits as well which enables gradients computation using only bit-wise operation. Quantized recurrent neural networks were tested over the Penn Treebank dataset, and achieved comparable accuracy as their 32-bit counterparts using only 4-bits. Last but not least, we programmed a binary matrix multiplication GPU kernel with which it is possible to run our MNIST QNN 7 times faster than with an unoptimized GPU kernel, without suffering any loss in classification accuracy. The QNN code is available online.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

The record

Venue
arXiv (Cornell University)
Topic
Neural Networks and Applications
Field
Computer Science
Canadian institutions
Université de Montréal
Funders
Keywords
Artificial neural networkComputer scienceArtificial intelligenceTraining (meteorology)Deep neural networksMachine learningPattern recognition (psychology)
Has abstract in OpenAlex
yes