The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Surat ini membentangkan teknik baru untuk mencapai inferens pantas rangkaian neural convolutional binarized (BCNN). Teknik yang dicadangkan mengubah suai struktur blok konstituen model BCNN supaya elemen input untuk operasi pengumpulan maksimum adalah binari. Dalam struktur ini, jika mana-mana elemen input ialah +1, hasil pengumpulan boleh dihasilkan serta-merta; teknik yang dicadangkan menghapuskan pengiraan sedemikian yang terlibat untuk mendapatkan elemen input yang tinggal, untuk mengurangkan masa inferens dengan berkesan. Teknik yang dicadangkan mengurangkan masa inferens sehingga 34.11%, sambil mengekalkan ketepatan pengelasan.
Ji-Hoon SHIN
Korea Aerospace University
Tae-Hwan KIM
Korea Aerospace University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Salinan
Ji-Hoon SHIN, Tae-Hwan KIM, "Fast Inference of Binarized Convolutional Neural Networks Exploiting Max Pooling with Modified Block Structure" in IEICE TRANSACTIONS on Information,
vol. E103-D, no. 3, pp. 706-710, March 2020, doi: 10.1587/transinf.2019EDL8165.
Abstract: This letter presents a novel technique to achieve a fast inference of the binarized convolutional neural networks (BCNN). The proposed technique modifies the structure of the constituent blocks of the BCNN model so that the input elements for the max-pooling operation are binary. In this structure, if any of the input elements is +1, the result of the pooling can be produced immediately; the proposed technique eliminates such computations that are involved to obtain the remaining input elements, so as to reduce the inference time effectively. The proposed technique reduces the inference time by up to 34.11%, while maintaining the classification accuracy.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2019EDL8165/_p
Salinan
@ARTICLE{e103-d_3_706,
author={Ji-Hoon SHIN, Tae-Hwan KIM, },
journal={IEICE TRANSACTIONS on Information},
title={Fast Inference of Binarized Convolutional Neural Networks Exploiting Max Pooling with Modified Block Structure},
year={2020},
volume={E103-D},
number={3},
pages={706-710},
abstract={This letter presents a novel technique to achieve a fast inference of the binarized convolutional neural networks (BCNN). The proposed technique modifies the structure of the constituent blocks of the BCNN model so that the input elements for the max-pooling operation are binary. In this structure, if any of the input elements is +1, the result of the pooling can be produced immediately; the proposed technique eliminates such computations that are involved to obtain the remaining input elements, so as to reduce the inference time effectively. The proposed technique reduces the inference time by up to 34.11%, while maintaining the classification accuracy.},
keywords={},
doi={10.1587/transinf.2019EDL8165},
ISSN={1745-1361},
month={March},}
Salinan
TY - JOUR
TI - Fast Inference of Binarized Convolutional Neural Networks Exploiting Max Pooling with Modified Block Structure
T2 - IEICE TRANSACTIONS on Information
SP - 706
EP - 710
AU - Ji-Hoon SHIN
AU - Tae-Hwan KIM
PY - 2020
DO - 10.1587/transinf.2019EDL8165
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E103-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2020
AB - This letter presents a novel technique to achieve a fast inference of the binarized convolutional neural networks (BCNN). The proposed technique modifies the structure of the constituent blocks of the BCNN model so that the input elements for the max-pooling operation are binary. In this structure, if any of the input elements is +1, the result of the pooling can be produced immediately; the proposed technique eliminates such computations that are involved to obtain the remaining input elements, so as to reduce the inference time effectively. The proposed technique reduces the inference time by up to 34.11%, while maintaining the classification accuracy.
ER -