JP7336819B2 - 抵抗処理ユニット・アレイのクロスポイント・デバイスに重みを記憶するための方法、そのクロスポイント・デバイス、ニューラル・ネットワークを実施するためのクロスポイント・アレイ、そのシステム、およびニューラル・ネットワークを実施するための方法 - Google Patents

抵抗処理ユニット・アレイのクロスポイント・デバイスに重みを記憶するための方法、そのクロスポイント・デバイス、ニューラル・ネットワークを実施するためのクロスポイント・アレイ、そのシステム、およびニューラル・ネットワークを実施するための方法 Download PDF

Info

Publication number
JP7336819B2
JP7336819B2 JP2020531461A JP2020531461A JP7336819B2 JP 7336819 B2 JP7336819 B2 JP 7336819B2 JP 2020531461 A JP2020531461 A JP 2020531461A JP 2020531461 A JP2020531461 A JP 2020531461A JP 7336819 B2 JP7336819 B2 JP 7336819B2
Authority
JP
Japan
Prior art keywords
crosspoint
array
resistor
counter
bit
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.)
Active
Application number
JP2020531461A
Other languages
English (en)
Japanese (ja)
Other versions
JP2021507349A5 (cg-RX-API-DMAC7.html
JP2021507349A (ja
Inventor
コスワッタ、シユランガ
リ、ユーロン
ソロモン、ポール、マイケル
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
International Business Machines Corp
Original Assignee
International Business Machines Corp
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by International Business Machines Corp filed Critical International Business Machines Corp
Publication of JP2021507349A publication Critical patent/JP2021507349A/ja
Publication of JP2021507349A5 publication Critical patent/JP2021507349A5/ja
Application granted granted Critical
Publication of JP7336819B2 publication Critical patent/JP7336819B2/ja
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
    • G06N3/063—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using electronic means
    • G06N3/065—Analogue means
    • H—ELECTRICITY
    • H03—ELECTRONIC CIRCUITRY
    • H03K—PULSE TECHNIQUE
    • H03K19/00—Logic circuits, i.e. having at least two inputs acting on one output; Inverting circuits
    • H03K19/20—Logic circuits, i.e. having at least two inputs acting on one output; Inverting circuits characterised by logic function, e.g. AND, OR, NOR, NOT circuits
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0499—Feedforward networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/09—Supervised learning

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Mathematical Physics (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Molecular Biology (AREA)
  • Data Mining & Analysis (AREA)
  • General Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Software Systems (AREA)
  • Computational Linguistics (AREA)
  • Computer Hardware Design (AREA)
  • Neurology (AREA)
  • Semiconductor Memories (AREA)
  • Electronic Switches (AREA)
  • Image Analysis (AREA)
  • Logic Circuits (AREA)
JP2020531461A 2017-12-13 2018-11-22 抵抗処理ユニット・アレイのクロスポイント・デバイスに重みを記憶するための方法、そのクロスポイント・デバイス、ニューラル・ネットワークを実施するためのクロスポイント・アレイ、そのシステム、およびニューラル・ネットワークを実施するための方法 Active JP7336819B2 (ja)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US15/840,322 2017-12-13
US15/840,322 US11222259B2 (en) 2017-12-13 2017-12-13 Counter based resistive processing unit for programmable and reconfigurable artificial-neural-networks
PCT/IB2018/059228 WO2019116128A1 (en) 2017-12-13 2018-11-22 Counter based resistive processing unit for programmable and reconfigurable artificial-neural-networks

Publications (3)

Publication Number Publication Date
JP2021507349A JP2021507349A (ja) 2021-02-22
JP2021507349A5 JP2021507349A5 (cg-RX-API-DMAC7.html) 2021-04-01
JP7336819B2 true JP7336819B2 (ja) 2023-09-01

Family

ID=66696262

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2020531461A Active JP7336819B2 (ja) 2017-12-13 2018-11-22 抵抗処理ユニット・アレイのクロスポイント・デバイスに重みを記憶するための方法、そのクロスポイント・デバイス、ニューラル・ネットワークを実施するためのクロスポイント・アレイ、そのシステム、およびニューラル・ネットワークを実施するための方法

Country Status (6)

Country Link
US (3) US11222259B2 (cg-RX-API-DMAC7.html)
JP (1) JP7336819B2 (cg-RX-API-DMAC7.html)
CN (1) CN111433792B (cg-RX-API-DMAC7.html)
DE (1) DE112018005726B4 (cg-RX-API-DMAC7.html)
GB (1) GB2582088B (cg-RX-API-DMAC7.html)
WO (1) WO2019116128A1 (cg-RX-API-DMAC7.html)

Families Citing this family (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20180136202A (ko) * 2017-06-14 2018-12-24 에스케이하이닉스 주식회사 컨볼루션 신경망 및 컨볼루션 신경망을 가진 신경망 시스템
US10303998B2 (en) * 2017-09-28 2019-05-28 International Business Machines Corporation Floating gate for neural network inference
US11222259B2 (en) 2017-12-13 2022-01-11 International Business Machines Corporation Counter based resistive processing unit for programmable and reconfigurable artificial-neural-networks
US11645536B2 (en) * 2018-01-24 2023-05-09 Wai Kit Ricky FOK Parallel residual neural network architecture and system and method for training a residual neural network
US20190251430A1 (en) * 2018-02-13 2019-08-15 International Business Machines Corporation Mixed signal cmos rpu with digital weight storage
US11403529B2 (en) * 2018-04-05 2022-08-02 Western Digital Technologies, Inc. Noise injection training for memory-based learning
US10601471B1 (en) 2018-08-29 2020-03-24 Micron Technology, Inc. Neuron calculator for artificial neural networks
JP2020077300A (ja) * 2018-11-09 2020-05-21 日本電信電話株式会社 分散深層学習システムおよびデータ転送方法
US11449730B2 (en) * 2018-12-24 2022-09-20 Wipro Limited Method and system for verifying classification performed by an artificial neural network
US20210034953A1 (en) * 2019-08-02 2021-02-04 Applied Materials, Inc. Reconfigurable finfet-based artificial neuron and synapse devices
CN110796241B (zh) * 2019-11-01 2022-06-17 清华大学 基于忆阻器的神经网络的训练方法及其训练装置
US11676031B2 (en) 2020-02-25 2023-06-13 Ventech Solutions, Inc. Anatomical position monitoring for bodily pressure ulcers
US20230080172A1 (en) * 2020-03-13 2023-03-16 Hewlett-Packard Development Company, L.P. Transmitting node instructions
US11651107B2 (en) 2020-03-17 2023-05-16 Ventech Solutions, Inc. Securing personally identifiable and private information in conversational AI-based communication
US11568262B2 (en) 2020-03-25 2023-01-31 Ventech Solutions, Inc. Neural network based radiowave monitoring of fall characteristics in injury diagnosis
US11133063B1 (en) * 2020-06-22 2021-09-28 International Business Machines Corporation Suppressing undesired programming at half-selected devices in a crosspoint array of 3-terminal resistive memory
CN113052306B (zh) * 2021-03-04 2022-04-22 华南理工大学 一种基于堆叠式宽度学习模型的在线学习芯片
US12450518B2 (en) * 2021-03-29 2025-10-21 Google Llc Evaluating on-device machine learning model(s) based on performance measures of client device(s) and/or the on-device machine learning model(s)
CN113437964B (zh) * 2021-06-10 2022-09-16 安徽大学 一种由rram构成的可阻态区分且可重构的运算电路
US11900979B2 (en) * 2021-10-22 2024-02-13 Intel Corporation Probabilistic in-memory computing
US20240249132A1 (en) * 2023-01-23 2024-07-25 Brisk Computing LLC Multi-resistor unit cell configuration for impementaiton in analog neuromorphic circuits
WO2025128671A1 (en) * 2023-12-12 2025-06-19 Massachusetts Institute Of Technology Ai training core based on dynamic programmable resistor array

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2017136100A2 (en) 2016-02-01 2017-08-10 Qualcomm Incorporated Vertically stacked nanowire field effect transistors

Family Cites Families (42)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US2715656A (en) 1952-08-02 1955-08-16 Bell Telephone Labor Inc Electrical information system
US4874963A (en) * 1988-02-11 1989-10-17 Bell Communications Research, Inc. Neuromorphic learning networks
JPH02236659A (ja) * 1989-03-09 1990-09-19 Fujitsu Ltd 半導体情報処理装置
JP2517410B2 (ja) 1989-05-15 1996-07-24 三菱電機株式会社 学習機能付集積回路装置
JPH0634248B2 (ja) * 1989-12-16 1994-05-02 三菱電機株式会社 半導体神経回路網
JPH06215163A (ja) * 1993-01-18 1994-08-05 Hitachi Ltd ニューラルネット構築支援方法及び装置、ニューラルネットテスト装置、薬注制御システム
JPH0884078A (ja) * 1994-09-09 1996-03-26 Fujitsu Ltd D/a変換器
US6185143B1 (en) 2000-02-04 2001-02-06 Hewlett-Packard Company Magnetic random access memory (MRAM) device including differential sense amplifiers
US6876989B2 (en) 2002-02-13 2005-04-05 Winbond Electronics Corporation Back-propagation neural network with enhanced neuron characteristics
US7079436B2 (en) * 2003-09-30 2006-07-18 Hewlett-Packard Development Company, L.P. Resistive cross point memory
US6990030B2 (en) * 2003-10-21 2006-01-24 Hewlett-Packard Development Company, L.P. Magnetic memory having a calibration system
US7913130B2 (en) * 2003-10-31 2011-03-22 Hewlett-Packard Development Company, L.P. Multi-sample read circuit having test mode of operation
US7576565B2 (en) * 2006-04-03 2009-08-18 Blaise Laurent Mouttet Crossbar waveform driver circuit
US7826248B2 (en) 2008-05-20 2010-11-02 Seagate Technology Llc Write verify method for resistive random access memory
US8009455B2 (en) 2009-01-20 2011-08-30 Ovonyx, Inc. Programmable resistance memory
US8275727B2 (en) * 2009-11-13 2012-09-25 International Business Machines Corporation Hardware analog-digital neural networks
US8655813B2 (en) * 2010-12-30 2014-02-18 International Business Machines Corporation Synaptic weight normalized spiking neuronal networks
US8856055B2 (en) 2011-04-08 2014-10-07 International Business Machines Corporation Reconfigurable and customizable general-purpose circuits for neural networks
US8812414B2 (en) * 2011-05-31 2014-08-19 International Business Machines Corporation Low-power event-driven neural computing architecture in neural networks
US8542521B2 (en) 2011-09-12 2013-09-24 Kabushiki Kaisha Toshiba Semiconductor storage device including memory cells capable of holding data
US9015092B2 (en) 2012-06-04 2015-04-21 Brain Corporation Dynamically reconfigurable stochastic learning apparatus and methods
US9412446B1 (en) 2013-08-16 2016-08-09 Sandia Corporation Multilevel resistive information storage and retrieval
US9812196B2 (en) 2013-10-28 2017-11-07 Hewlett Packard Enterprise Development Lp Geometry dependent voltage biases for asymmetric resistive memories
KR102267237B1 (ko) * 2014-03-07 2021-06-18 가부시키가이샤 한도오따이 에네루기 켄큐쇼 반도체 장치 및 전자 기기
US20150278682A1 (en) * 2014-04-01 2015-10-01 Boise State University Memory controlled circuit system and apparatus
US9466362B2 (en) * 2014-08-12 2016-10-11 Arizona Board Of Regents On Behalf Of Arizona State University Resistive cross-point architecture for robust data representation with arbitrary precision
US9934463B2 (en) * 2015-05-15 2018-04-03 Arizona Board Of Regents On Behalf Of Arizona State University Neuromorphic computational system(s) using resistive synaptic devices
US9847125B2 (en) 2015-08-05 2017-12-19 University Of Rochester Resistive memory accelerator
US10387778B2 (en) * 2015-09-29 2019-08-20 International Business Machines Corporation Scalable architecture for implementing maximization algorithms with resistive devices
US10248907B2 (en) 2015-10-20 2019-04-02 International Business Machines Corporation Resistive processing unit
US10901939B2 (en) 2015-10-30 2021-01-26 International Business Machines Corporation Computer architecture with resistive processing units
US10671911B2 (en) * 2016-02-19 2020-06-02 International Business Machines Corporation Current mirror scheme for an integrating neuron circuit
EP3262571B1 (en) * 2016-03-11 2022-03-02 Hewlett Packard Enterprise Development LP Hardware accelerators for calculating node values of neural networks
CN106158017B (zh) * 2016-06-20 2019-05-17 北京大学 阻变运算存储设备
US9715656B1 (en) 2016-09-12 2017-07-25 International Business Machines Corporation Killing asymmetric resistive processing units for neural network training
US9646243B1 (en) 2016-09-12 2017-05-09 International Business Machines Corporation Convolutional neural networks using resistive processing unit array
US9779355B1 (en) 2016-09-15 2017-10-03 International Business Machines Corporation Back propagation gates and storage capacitor for neural networks
US9659249B1 (en) * 2016-09-27 2017-05-23 International Business Machines Corporation Pre-programmed resistive cross-point array for neural network
US10482929B2 (en) * 2017-07-13 2019-11-19 Qualcomm Incorporated Non-volative (NV) memory (NVM) matrix circuits employing NVM matrix circuits for performing matrix computations
US10127494B1 (en) * 2017-08-02 2018-11-13 Google Llc Neural network crossbar stack
US11222259B2 (en) 2017-12-13 2022-01-11 International Business Machines Corporation Counter based resistive processing unit for programmable and reconfigurable artificial-neural-networks
US11087204B2 (en) * 2018-04-20 2021-08-10 International Business Machines Corporation Resistive processing unit with multiple weight readers

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2017136100A2 (en) 2016-02-01 2017-08-10 Qualcomm Incorporated Vertically stacked nanowire field effect transistors

Also Published As

Publication number Publication date
WO2019116128A1 (en) 2019-06-20
GB2582088B (en) 2022-07-27
US20220058474A1 (en) 2022-02-24
DE112018005726T5 (de) 2020-07-16
JP2021507349A (ja) 2021-02-22
GB2582088A (en) 2020-09-09
US20190180174A1 (en) 2019-06-13
CN111433792B (zh) 2023-11-21
US12423568B2 (en) 2025-09-23
DE112018005726B4 (de) 2022-04-21
US11222259B2 (en) 2022-01-11
US20240086697A1 (en) 2024-03-14
GB202007432D0 (en) 2020-07-01
US11875249B2 (en) 2024-01-16
CN111433792A (zh) 2020-07-17

Similar Documents

Publication Publication Date Title
US12423568B2 (en) Counter based resistive processing unit for programmable and reconfigurable artificial-neural-networks
CN110352436B (zh) 用于神经网络训练的具有迟滞更新的电阻处理单元
CN107924227B (zh) 电阻处理单元
US11727977B2 (en) Non-volatile analog resistive memory cells implementing ferroelectric select transistors
US11087204B2 (en) Resistive processing unit with multiple weight readers
US9779355B1 (en) Back propagation gates and storage capacitor for neural networks
JP7130766B2 (ja) 効率的な行列乗算のためのシステムおよび方法
US10708522B2 (en) Image sensor with analog sample and hold circuit control for analog neural networks
US20210151102A1 (en) Circuit methodology for highly linear and symmetric resistive processing unit
US9466362B2 (en) Resistive cross-point architecture for robust data representation with arbitrary precision
CN107533668B (zh) 用于计算神经网络的节点值的硬件加速器和方法
JP7357079B2 (ja) 相変化メモリの閉ループ・プログラミング
US10381074B1 (en) Differential weight reading of an analog memory element in crosspoint array utilizing current subtraction transistors
US12050997B2 (en) Row-by-row convolutional neural network mapping for analog artificial intelligence network training
CN115699028B (zh) 模拟人工智能网络推理的逐行卷积神经网络映射的高效瓦片映射
US10832773B1 (en) Architecture for enabling zero value shifting
Yang et al. On learning with nonlinear memristor-based neural network and its replication
US11586899B2 (en) Neuromorphic device with oxygen scavenging gate
WO2024131362A1 (en) Non-volatile memory-based activation function
US11195089B2 (en) Multi-terminal cross-point synaptic device using nanocrystal dot structures
AU2021296187B2 (en) Suppressing undesired programming at half-selected devices in a crosspoint array of 3-terminal resistive memory
CN120322776A (zh) 用于乘法累加操作的固定非对称性补偿

Legal Events

Date Code Title Description
A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20210128

A621 Written request for application examination

Free format text: JAPANESE INTERMEDIATE CODE: A621

Effective date: 20210423

RD04 Notification of resignation of power of attorney

Free format text: JAPANESE INTERMEDIATE CODE: A7424

Effective date: 20220502

A977 Report on retrieval

Free format text: JAPANESE INTERMEDIATE CODE: A971007

Effective date: 20220531

A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20220621

RD12 Notification of acceptance of power of sub attorney

Free format text: JAPANESE INTERMEDIATE CODE: A7432

Effective date: 20220902

A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20220921

A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20230124

A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20230417

TRDD Decision of grant or rejection written
A01 Written decision to grant a patent or to grant a registration (utility model)

Free format text: JAPANESE INTERMEDIATE CODE: A01

Effective date: 20230801

RD14 Notification of resignation of power of sub attorney

Free format text: JAPANESE INTERMEDIATE CODE: A7434

Effective date: 20230802

A61 First payment of annual fees (during grant procedure)

Free format text: JAPANESE INTERMEDIATE CODE: A61

Effective date: 20230817

R150 Certificate of patent or registration of utility model

Ref document number: 7336819

Country of ref document: JP

Free format text: JAPANESE INTERMEDIATE CODE: R150