@inproceedings{de_prado_quenn:_2018,
	title = {{QUENN}: {QUantization} {Engine} for low-power {Neural} {Networks}},
	shorttitle = {{QUENN}},
	url = {https://arxiv.org/abs/1811.05896v1},
	doi = {10.1145/3203217.3203282},
	abstract = {Deep Learning is moving to edge devices, ushering in a new age of distributed
Artificial Intelligence (AI). The high demand of computational resources
required by deep neural networks may be alleviated by approximate computing
techniques, and most notably reduced-precision arithmetic with coarsely
quantized numerical representations. In this context, Bonseyes comes in as an
initiative to enable stakeholders to bring AI to low-power and autonomous
environments such as: Automotive, Medical Healthcare and Consumer Electronics.
To achieve this, we introduce LPDNN, a framework for optimized deployment of
Deep Neural Networks on heterogeneous embedded devices. In this work, we detail
the quantization engine that is integrated in LPDNN. The engine depends on a
fine-grained workflow which enables a Neural Network Design Exploration and a
sensitivity analysis of each layer for quantization. We demonstrate the engine
with a case study on Alexnet and VGG16 for three different techniques for
direct quantization: standard fixed-point, dynamic fixed-point and k-means
clustering, and demonstrate the potential of the latter. We argue that using a
Gaussian quantizer with k-means clustering can achieve better performance than
linear quantizers. Without retraining, we achieve over 55.64{\textbackslash}\% saving for
weights' storage and 69.17{\textbackslash}\% for run-time memory accesses with less than 1{\textbackslash}\%
drop in top5 accuracy in Imagenet.},
	language = {en},
	urldate = {2019-01-29TZ},
	booktitle = {{CF} '18 {Proceedings} of the 15th {ACM} {International} {Conference} on {Computing} {Frontiers}},
	author = {de Prado, Miguel and Denna, Maurizio and Benini, Luca and Pazos, Nuria},
	month = nov,
	year = {2018},
	note = {ACM International Conference on Computing Frontiers 2018}
}