@inproceedings{de_prado_quenn:_2018,
	title = {{QUENN}: {QUantization} Engine for low-power Neural Networks},
	url = {https://arxiv.org/abs/1811.05896v1},
	doi = {10.1145/3203217.3203282},
	shorttitle = {{QUENN}},
	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 {VGG}16 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.},
	eventtitle = {{CF} '18 15th {ACM} International Conference on Computing Frontiers},
	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},
	urldate = {2019-01-29},
	date = {2018-11-14},
	langid = {english},
	note = {{ACM} International Conference on Computing Frontiers 2018},
}