Title:
DECOMPRESSION APPARATUS AND CONTROL METHOD THEREOF
Document Type and Number:
WIPO Patent Application WO/2020/242057
Kind Code:
A1
Abstract:
A decompression apparatus is provided. The decompression apparatus includes a memory configured to store compressed data decompressed and used in neural network processing of an artificial intelligence model, a decoder configured to include a plurality of logic circuits related to a compression method of the compressed data, decompress the compressed data through the plurality of logic circuits based on an input of the compressed data, and output the decompressed data, and a processor configured to obtain data of a neural network processible form from the data output from the decoder.
Inventors:
LEE DONGSOO (KR)
KWON SEJUNG (KR)
KIM BYEOUNGWOOK (KR)
KAPOOR PARICHAY (KR)
PARK BAESEONG (KR)
KWON SEJUNG (KR)
KIM BYEOUNGWOOK (KR)
KAPOOR PARICHAY (KR)
PARK BAESEONG (KR)
Application Number:
PCT/KR2020/005269
Publication Date:
December 03, 2020
Filing Date:
April 22, 2020
Export Citation:
Assignee:
SAMSUNG ELECTRONICS CO LTD (KR)
International Classes:
G06N3/04; G06N3/08; H04N19/13; H04N19/70
Foreign References:
| CN107832837A | 2018-03-23 | |||
| KR20180052069A | 2018-05-17 |
Other References:
SIAN JIN; SHENG DI; XIN LIANG; JIANNAN TIAN; DINGWEN TAO; FRANCK CAPPELLO: "DeepSZ: A Novel Framework to Compress Deep Neural Networks by Using Error-Bounded Lossy Compression", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 26 January 2019 (2019-01-26), 201 Olin Library Cornell University Ithaca, NY 14853, XP081161603, DOI: 10.1145/3307681.3326608
DONGSOO LEE, SE JUNG KWON, BYEONGWOOK KIM, PARICHAY KAPOOR, GU-YEON WEI: "Network Pruning for Low-Rank Binary Indexing", 14 May 2019 (2019-05-14), XP055701725, Retrieved from the Internet
YU CHENG et al., `A Survey of Model Compression and Acceleration for Deep Neural Networks`, arXiv:1710.09282v7, 07 February 2019 [retrieved on 2020.07.27]. Retrieved from page 7; and figure 1
DONGSOO LEE, SE JUNG KWON, BYEONGWOOK KIM, PARICHAY KAPOOR, GU-YEON WEI: "Network Pruning for Low-Rank Binary Indexing", 14 May 2019 (2019-05-14), XP055701725, Retrieved from the Internet
YU CHENG et al., `A Survey of Model Compression and Acceleration for Deep Neural Networks`, arXiv:1710.09282v7, 07 February 2019 [retrieved on 2020.07.27]. Retrieved from
Attorney, Agent or Firm:
KIM, Tae-hun et al. (KR)
Download PDF:
Previous Patent: HAIRBRUSH HAVING SCALP AND HAIR MANAGEMENT FUNCTION
Next Patent: DEVICE IN MULTICAST GROUP
Next Patent: DEVICE IN MULTICAST GROUP