Warning: Undefined array key "user" in /home/clients/74149e9e6fa5a1aab2af4ee83f7c0551/web/bonseyes/outcomes/get_item.php on line 11
@inproceedings{de_prado_learning_2019,
title = {Learning to infer: {RL}-based search for {DNN} primitive selection on Heterogeneous Embedded Systems},
url = {https://arxiv.org/abs/1811.07315v1},
doi = {https://doi.org/10.23919/DATE.2019.8714959},
shorttitle = {Learning to infer},
abstract = {Deep Learning is increasingly being adopted by industry for computer vision
applications running on embedded devices. While Convolutional Neural Networks'
accuracy has achieved a mature and remarkable state, inference latency and
throughput are a major concern especially when targeting low-cost and low-power
embedded platforms. {CNNs}' inference latency may become a bottleneck for Deep
Learning adoption by industry, as it is a crucial specification for many
real-time processes. Furthermore, deployment of {CNNs} across heterogeneous
platforms presents major compatibility issues due to vendor-specific technology
and acceleration libraries. In this work, we present {QS}-{DNN}, a fully automatic
search based on Reinforcement Learning which, combined with an inference engine
optimizer, efficiently explores through the design space and empirically finds
the optimal combinations of libraries and primitives to speed up the inference
of {CNNs} on heterogeneous embedded devices. We show that, an optimized
combination can achieve 45x speedup in inference latency on {CPU} compared to a
dependency-free baseline and 2x on average on {GPGPU} compared to the best vendor
library. Further, we demonstrate that, the quality of results and time
"to-solution" is much better than with Random Search and achieves up to 15x
better results for a short-time search.},
eventtitle = {{DATE} 2019},
booktitle = {Proceedings of Design, Automation and Test in Europe Conference, {DATE} 19. March 2019},
author = {de Prado, Miguel and Pazos, Nuria and Benini, Luca},
urldate = {2019-01-29},
date = {2019},
langid = {english},
}