Title:
ELECTRONIC DEVICE AND CONTROL METHOD THEREFOR
Document Type and Number:
WIPO Patent Application WO/2022/075600
Kind Code:
A1
Abstract:
An electronic device and a control method therefor are disclosed. An electronic device of the present disclosure comprises: a memory for storing first input data and weight data used for calculation of a neural network model; and a processor, which quantizes the weight data with a combination of sign data and scaling factor data to obtain quantized data, wherein the processor can: input the first input data into a first module to obtain second input data in which exponents of input values included in the first input data are converted to the same value; input the second input data and the sign data into a second module to determine the signs of input values included in the second input data, and perform calculations between the input values having the determined signs, so as to obtain first output data; input the first output data into a third module to normalize output values included in the first output data; and perform a multiplication operation on data including the normalized output values and the scaling factor data, so as to obtain second output data.
More Like This:
Inventors:
KIM BYEOUNGWOOK (KR)
LEE DONGSOO (KR)
KWON SEJUNG (KR)
RO YEONJU (KR)
PARK BAESEONG (KR)
JEON YONGKWEON (KR)
LEE DONGSOO (KR)
KWON SEJUNG (KR)
RO YEONJU (KR)
PARK BAESEONG (KR)
JEON YONGKWEON (KR)
Application Number:
PCT/KR2021/011740
Publication Date:
April 14, 2022
Filing Date:
September 01, 2021
Export Citation:
Assignee:
SAMSUNG ELECTRONICS CO LTD (KR)
International Classes:
G06N3/063; G06N3/04; G06N3/08
Foreign References:
| CN111696149A | 2020-09-22 | |||
| US20190205741A1 | 2019-07-04 | |||
| US20180005111A1 | 2018-01-04 | |||
| US20190205746A1 | 2019-07-04 | |||
| KR20200091785A | 2020-07-31 |
Other References:
LI YANG; BAO YUANYUAN; CHEN WAI: "Fixed-Sign Binary Neural Network: An Efficient Design of Neural Network for Internet-of-Things Devices", IEEE ACCESS, IEEE, USA, vol. 8, 9 September 2020 (2020-09-09), USA , pages 164858 - 164863, XP011809874, DOI: 10.1109/ACCESS.2020.3022902
DIPANKAR DAS ET AL: "Mixed Precision Training of Convolutional Neural Networks using Integer Operations", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 3 February 2018 (2018-02-03), 201 Olin Library Cornell University Ithaca, NY 14853 , pages 1 - 11, XP080857087
DIPANKAR DAS ET AL: "Mixed Precision Training of Convolutional Neural Networks using Integer Operations", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 3 February 2018 (2018-02-03), 201 Olin Library Cornell University Ithaca, NY 14853 , pages 1 - 11, XP080857087
Attorney, Agent or Firm:
KIM, Tae-hun et al. (KR)
Download PDF:
Previous Patent: MASSAGE DEVICE FOR PROVIDING MEDITATIVE MASSAGE
Next Patent: HETEROCYCLIC COMPOUND AND ORGANIC LIGHT-EMITTING DEVICE COMPRISING SAME
Next Patent: HETEROCYCLIC COMPOUND AND ORGANIC LIGHT-EMITTING DEVICE COMPRISING SAME