JPWO2022009449A5 - - Google Patents

Download PDF

Info

Publication number
JPWO2022009449A5
JPWO2022009449A5 JP2022534893A JP2022534893A JPWO2022009449A5 JP WO2022009449 A5 JPWO2022009449 A5 JP WO2022009449A5 JP 2022534893 A JP2022534893 A JP 2022534893A JP 2022534893 A JP2022534893 A JP 2022534893A JP WO2022009449 A5 JPWO2022009449 A5 JP WO2022009449A5
Authority
JP
Japan
Prior art keywords
information processing
processor
quantizing
quantized
quantization
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Withdrawn
Application number
JP2022534893A
Other languages
English (en)
Japanese (ja)
Other versions
JPWO2022009449A1 (cg-RX-API-DMAC7.html
Filing date
Publication date
Priority claimed from PCT/JP2020/027134 external-priority patent/WO2022009433A1/ja
Application filed filed Critical
Publication of JPWO2022009449A1 publication Critical patent/JPWO2022009449A1/ja
Publication of JPWO2022009449A5 publication Critical patent/JPWO2022009449A5/ja
Withdrawn legal-status Critical Current

Links

JP2022534893A 2020-07-10 2020-12-22 Withdrawn JPWO2022009449A1 (cg-RX-API-DMAC7.html)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
PCT/JP2020/027134 WO2022009433A1 (ja) 2020-07-10 2020-07-10 情報処理装置,情報処理方法および情報処理プログラム
PCT/JP2020/047958 WO2022009449A1 (ja) 2020-07-10 2020-12-22 情報処理装置,情報処理方法および情報処理プログラム

Publications (2)

Publication Number Publication Date
JPWO2022009449A1 JPWO2022009449A1 (cg-RX-API-DMAC7.html) 2022-01-13
JPWO2022009449A5 true JPWO2022009449A5 (cg-RX-API-DMAC7.html) 2023-01-24

Family

ID=79553188

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2022534893A Withdrawn JPWO2022009449A1 (cg-RX-API-DMAC7.html) 2020-07-10 2020-12-22

Country Status (5)

Country Link
US (1) US20230123756A1 (cg-RX-API-DMAC7.html)
EP (1) EP4181022A1 (cg-RX-API-DMAC7.html)
JP (1) JPWO2022009449A1 (cg-RX-API-DMAC7.html)
CN (1) CN115917560A (cg-RX-API-DMAC7.html)
WO (2) WO2022009433A1 (cg-RX-API-DMAC7.html)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20240070518A1 (en) * 2022-08-26 2024-02-29 Dell Products L.P. Smart communication in federated learning for transient and resource-constrained mobile edge devices
CN116187387B (zh) * 2023-02-22 2026-04-10 伟光有限公司 神经网络模型量化方法、装置、计算机设备和存储介质
JP2025096942A (ja) * 2023-12-18 2025-06-30 マクセル株式会社 学習方法及び学習装置
US20250265239A1 (en) * 2024-02-21 2025-08-21 Macronix International Co., Ltd. Quantization Error Compensation for Vector Computing

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0784975A (ja) * 1993-09-10 1995-03-31 Hitachi Ltd 情報処理装置および学習演算処理方法
CN108345939B (zh) * 2017-01-25 2022-05-24 微软技术许可有限责任公司 基于定点运算的神经网络
JP6823495B2 (ja) * 2017-02-27 2021-02-03 株式会社日立製作所 情報処理装置および画像認識装置
KR102526818B1 (ko) 2017-07-07 2023-04-27 미쓰비시덴키 가부시키가이샤 데이터 처리 장치, 데이터 처리 방법 및 기억 매체
KR102601604B1 (ko) * 2017-08-04 2023-11-13 삼성전자주식회사 뉴럴 네트워크의 파라미터들을 양자화하는 방법 및 장치
KR102564456B1 (ko) * 2017-10-19 2023-08-07 삼성전자주식회사 뉴럴 네트워크의 파라미터를 양자화하는 장치 및 방법
JP2019080232A (ja) * 2017-10-26 2019-05-23 株式会社Preferred Networks 勾配圧縮装置、勾配圧縮方法及びプログラム
GB2568084B (en) * 2017-11-03 2022-01-12 Imagination Tech Ltd Error allocation format selection for hardware implementation of deep neural network

Similar Documents

Publication Publication Date Title
KR102110486B1 (ko) 인공 뉴럴 네트워크 클래스-기반 프루닝
US10902318B2 (en) Methods and systems for improved transforms in convolutional neural networks
US20230316042A1 (en) Mixture of experts models with sparsified weights
CN110598838B (zh) 统计感知权重量化
US20190251441A1 (en) Reducing architectural complexity of convolutional neural networks via channel pruning
KR20210053160A (ko) 인공 신경망을 위한 구간 양자화 방법
US11551054B2 (en) System-aware selective quantization for performance optimized distributed deep learning
JP2021524099A5 (cg-RX-API-DMAC7.html)
CN111783961A (zh) 基于激活定点拟合的卷积神经网络训练后量化方法及系统
US11521622B2 (en) System and method for efficient processing of universal background models for speaker recognition
WO2021037174A1 (zh) 一种神经网络模型训练方法及装置
CN112288046A (zh) 一种用于神经网络的基于混合粒度的联合稀疏方法
CN110046706A (zh) 模型生成方法、装置及服务器
CN113241064B (zh) 语音识别、模型训练方法、装置、电子设备和存储介质
US12619854B2 (en) Neural network inference quantization
CN112598020B (zh) 目标识别方法及系统
CN108734287A (zh) 深度神经网络模型的压缩方法及装置、终端、存储介质
CN109493873A (zh) 牲畜声纹识别方法、装置、终端设备及计算机存储介质
CN114841339A (zh) 网络模型量化方法、装置、电子设备和存储介质
KR20230134877A (ko) 민감도-기반 양자화된 트레이닝을 수행하는 전자 장치 및 그 동작 방법
CN119443193A (zh) 一种多模态大模型的训练过程自适应优化方法及系统
CN113159121B (zh) 基于先验知识模型的机器人磨抛去除量预测方法及设备
CN109766476B (zh) 视频内容情感分析方法、装置、计算机设备及存储介质
CN118194954A (zh) 神经网络模型的训练方法及装置、电子设备和存储介质
CN121787485A (zh) 自适应混合精度量化方法、装置、设备及介质