Přejít na obsah

Detail publikace

Citace

M. Bulín and L. Šmídl and J. Švec : Towards Network Simplification for Low-Cost Devices by Removing Synapses . International Conference on Speech and Computer, p. 58-67, Springer, Cham, 2018.

PDF ke stažení

PDF

Další informace


Springer

Abstrakt

The deployment of robust neural network based models on low-cost devices touches the problem with hardware constraints like limited memory footprint and computing power. This work presents a general method for a rapid reduction of parameters (80–90%) in a trained (DNN or LSTM) network by removing its redundant synapses, while the classification accuracy is not significantly hurt. The massive reduction of parameters leads to a notable decrease of the model’s size and the actual prediction time of on-board classifiers. We show the pruning results on a simple speech recognition task, however, the method is applicable to any classification data.

Detail publikace

Název: Towards Network Simplification for Low-Cost Devices by Removing Synapses
Autor: M. Bulín ; L. Šmídl ; J. Švec
Jazyk publikace: anglicky
Datum vydání: 18.9.2018
Rok vydání: 2018
Typ publikace: Stať ve sborníku
Název časopisu / knihy: International Conference on Speech and Computer
Strana: 58 - 67
DOI: https://doi.org/10.1007/978-3-319-99579-3_7
ISBN: 978-3-319-99579-3
Nakladatel: Springer, Cham
Datum: 18.9.2018 - 22.9.2018
/ 2019-02-07 14:45:35 /

Klíčová slova

Pruning synapses, Network simplification, Minimal network structure, Low-cost devices, Speech recognition

BibTeX

@INPROCEEDINGS{MBulin_2018_TowardsNetwork,
 author = {M. Bul\'{i}n and L. \v{S}m\'{i}dl and J. \v{S}vec},
 title = {Towards Network Simplification for Low-Cost Devices by Removing Synapses},
 year = {2018},
 publisher = {Springer, Cham},
 journal = {International Conference on Speech and Computer},
 pages = {58-67},
 ISBN = {978-3-319-99579-3},
 doi = {https://doi.org/10.1007/978-3-319-99579-3_7},
 url = {http://www.kky.zcu.cz/en/publications/MBulin_2018_TowardsNetwork},
}