Title: | Towards network simplification for low-cost devices by removing synapses |
Authors: | Bulín, Martin Šmídl, Luboš Švec, Jan |
Citation: | BULÍN, Martin; ŠMÍDL, Luboš; ŠVEC, Jan. Towards network simplification for low-cost devices by removing synapses. In: International conference on speech and computer: SPECOM 2018. Cham: Springer, 2018, p. 58-67. (Lectures notes in computer science; 11096). ISBN 978-3-319-99579-3. |
Issue Date: | 2018 |
Publisher: | Springer |
Document type: | konferenční příspěvek conferenceObject |
URI: | http://hdl.handle.net/11025/34329 |
ISBN: | 978-3-319-99579-3 |
Keywords: | prořezávání synpsí;zjednodušení sítě;struktura minimální sítě;nízkonákladová zařízení;rozpoznávání řeči |
Keywords in different language: | pruning synapses;network simplification;minimal network structure;low-cost devices;speech recognition |
Abstract in different language: | 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. |
Rights: | © Springer |
Appears in Collections: | Konferenční příspěvky / Conference Papers (KKY) |
Please use this identifier to cite or link to this item:
http://hdl.handle.net/11025/34329
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.