JP2017507397A - 自動エラー訂正のための同時レイテンシおよびレートコーディング - Google Patents

自動エラー訂正のための同時レイテンシおよびレートコーディング Download PDF

Info

Publication number
JP2017507397A
JP2017507397A JP2016544506A JP2016544506A JP2017507397A JP 2017507397 A JP2017507397 A JP 2017507397A JP 2016544506 A JP2016544506 A JP 2016544506A JP 2016544506 A JP2016544506 A JP 2016544506A JP 2017507397 A JP2017507397 A JP 2017507397A
Authority
JP
Japan
Prior art keywords
spike
stimulus
spikes
train
neuron
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.)
Pending
Application number
JP2016544506A
Other languages
English (en)
Japanese (ja)
Other versions
JP2017507397A5 (enExample
Inventor
チャン、ビクター・ホッキウ
カーレイ、ライアン・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.)
Qualcomm Inc
Original Assignee
Qualcomm Inc
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 Qualcomm Inc filed Critical Qualcomm Inc
Publication of JP2017507397A publication Critical patent/JP2017507397A/ja
Publication of JP2017507397A5 publication Critical patent/JP2017507397A5/ja
Pending legal-status Critical Current

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
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0463—Neocognitrons
    • 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
    • G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
    • 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
    • G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
    • G06N3/061—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using biological neurons, e.g. biological neurons connected to an integrated circuit
    • 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
    • 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
    • G06N3/082—Learning methods modifying the architecture, e.g. adding, deleting or silencing nodes or connections

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Molecular Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Linguistics (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Neurology (AREA)
  • Microelectronics & Electronic Packaging (AREA)
  • Image Analysis (AREA)
  • Detection And Prevention Of Errors In Transmission (AREA)
  • Detection And Correction Of Errors (AREA)
JP2016544506A 2014-01-06 2014-12-19 自動エラー訂正のための同時レイテンシおよびレートコーディング Pending JP2017507397A (ja)

Applications Claiming Priority (5)

Application Number Priority Date Filing Date Title
US201461924074P 2014-01-06 2014-01-06
US61/924,074 2014-01-06
US14/279,375 US10282660B2 (en) 2014-01-06 2014-05-16 Simultaneous latency and rate coding for automatic error correction
US14/279,375 2014-05-16
PCT/US2014/071372 WO2015102935A2 (en) 2014-01-06 2014-12-19 Simultaneous latency and rate coding for automatic error correction

Publications (2)

Publication Number Publication Date
JP2017507397A true JP2017507397A (ja) 2017-03-16
JP2017507397A5 JP2017507397A5 (enExample) 2018-01-11

Family

ID=52350355

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2016544506A Pending JP2017507397A (ja) 2014-01-06 2014-12-19 自動エラー訂正のための同時レイテンシおよびレートコーディング

Country Status (6)

Country Link
US (1) US10282660B2 (enExample)
EP (1) EP3092605A2 (enExample)
JP (1) JP2017507397A (enExample)
CN (1) CN105874478A (enExample)
TW (1) TW201539336A (enExample)
WO (1) WO2015102935A2 (enExample)

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10671912B2 (en) * 2016-09-13 2020-06-02 Sap Se Spatio-temporal spiking neural networks in neuromorphic hardware systems
CN108304912B (zh) * 2017-12-29 2020-12-29 北京理工大学 一种运用抑制信号实现脉冲神经网络监督学习的系统和方法
CN109948788B (zh) * 2019-03-07 2021-01-15 清华大学 基于fpga的神经网络加速器
RU195230U1 (ru) * 2019-08-07 2020-01-17 Федеральное государственное бюджетное научное учреждение "Научный центр неврологии" (ФГБНУ НЦН) Тренажер-квадрат с линейными и квадратными углублениями для групповых занятий по восстановлению и профилактической тренировке зрительно-пространственной памяти
CN110647982B (zh) * 2019-09-26 2022-04-15 中国科学院微电子研究所 人工感受神经电路及其制备方法
KR102795609B1 (ko) 2019-11-25 2025-04-15 삼성전자주식회사 뉴로모픽 장치 및 이를 포함하는 뉴로모픽 시스템
FR3111455A1 (fr) * 2020-06-16 2021-12-17 Stmicroelectronics Sa Codage d’un flux de données
CN114528983B (zh) * 2021-12-29 2025-08-29 北京时代民芯科技有限公司 一种脉冲神经元加固电路、加固方法
CN116468086A (zh) * 2022-01-11 2023-07-21 北京灵汐科技有限公司 数据处理方法及装置、电子设备、计算机可读介质

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040204769A1 (en) * 2001-01-12 2004-10-14 Richmond Barry J. Decoding algorithm for neuronal reponses
JP2005267105A (ja) * 2004-03-17 2005-09-29 Canon Inc 並列パルス信号処理装置、パターン認識装置、及び画像入力装置
US20130151448A1 (en) * 2011-12-07 2013-06-13 Filip Ponulak Apparatus and methods for implementing learning for analog and spiking signals in artificial neural networks

Family Cites Families (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5107442A (en) * 1989-01-12 1992-04-21 Recognition Equipment Incorporated Adaptive neural network image processing system
US6581046B1 (en) * 1997-10-10 2003-06-17 Yeda Research And Development Co. Ltd. Neuronal phase-locked loops
JP4248187B2 (ja) 2002-03-27 2009-04-02 シャープ株式会社 集積回路装置及びニューロ素子
US7430546B1 (en) * 2003-06-07 2008-09-30 Roland Erwin Suri Applications of an algorithm that mimics cortical processing
US7395251B2 (en) 2005-07-01 2008-07-01 International Business Machines Corporation Neural networks for prediction and control
WO2008039331A1 (en) * 2006-09-22 2008-04-03 The Trustees Of The University Of Pennsylvania Classification of sub cortical structures
US8504502B2 (en) 2007-11-20 2013-08-06 Christopher Fiorillo Prediction by single neurons
US20130203027A1 (en) * 2010-06-28 2013-08-08 The Regents Of The University Of California Adaptive Set Discrimination Procedure
US10448877B2 (en) * 2010-12-05 2019-10-22 Brown University Methods for prediction and early detection of neurological events
US9964433B2 (en) * 2011-02-09 2018-05-08 The Trustees Of Dartmouth College Acoustic sensor with an acoustic object detector for reducing power consumption in front-end circuit
US9047568B1 (en) * 2012-09-20 2015-06-02 Brain Corporation Apparatus and methods for encoding of sensory data using artificial spiking neurons
US9256215B2 (en) 2012-07-27 2016-02-09 Brain Corporation Apparatus and methods for generalized state-dependent learning in spiking neuron networks
US9367798B2 (en) 2012-09-20 2016-06-14 Brain Corporation Spiking neuron network adaptive control apparatus and methods
US9189730B1 (en) * 2012-09-20 2015-11-17 Brain Corporation Modulated stochasticity spiking neuron network controller apparatus and methods
US9111226B2 (en) * 2012-10-25 2015-08-18 Brain Corporation Modulated plasticity apparatus and methods for spiking neuron network
US9177245B2 (en) * 2013-02-08 2015-11-03 Qualcomm Technologies Inc. Spiking network apparatus and method with bimodal spike-timing dependent plasticity

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040204769A1 (en) * 2001-01-12 2004-10-14 Richmond Barry J. Decoding algorithm for neuronal reponses
JP2005267105A (ja) * 2004-03-17 2005-09-29 Canon Inc 並列パルス信号処理装置、パターン認識装置、及び画像入力装置
US20130151448A1 (en) * 2011-12-07 2013-06-13 Filip Ponulak Apparatus and methods for implementing learning for analog and spiking signals in artificial neural networks

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
渡辺 正峰 外１名: "「デュアルコーディングとネットワークダイナミクス」", 電子情報通信学会技術研究報告, vol. 第１００巻，第１９１号, JPN6018041339, 11 July 2000 (2000-07-11), pages 31 - 36, ISSN: 0003903756 *

Also Published As

Publication number Publication date
CN105874478A (zh) 2016-08-17
TW201539336A (zh) 2015-10-16
EP3092605A2 (en) 2016-11-16
US10282660B2 (en) 2019-05-07
US20150193680A1 (en) 2015-07-09
WO2015102935A3 (en) 2015-10-08
WO2015102935A2 (en) 2015-07-09

Similar Documents

Publication Publication Date Title
JP2017507397A (ja) 自動エラー訂正のための同時レイテンシおよびレートコーディング
JP6130056B2 (ja) スパイキングネットワークの効率的なハードウェア実装
JP6275868B2 (ja) ニューラルウォッチドッグ
CN105934766B (zh) 用阴影网络来监视神经网络
JP2016538632A (ja) 教師あり学習を使用してクラスにタグ付けするための方法および装置
CN110110677B (zh) 摄影图像中的眨眼和转移注视避免
JP2017513127A (ja) スパイキング深層信念ネットワーク（ｄｂｎ）におけるトレーニング、認識、および生成
US9652711B2 (en) Analog signal reconstruction and recognition via sub-threshold modulation
US20150212861A1 (en) Value synchronization across neural processors
KR20160123309A (ko) 확률적 스파이킹 베이지안망들에 대한 이벤트-기반 추론 및 학습
JP2017514215A (ja) スパイキングニューラルネットワークを使用する画像の不変オブジェクト表現
JP2016539414A (ja) スパイキングニューラルネットワークにおいてリプレーを使用するシナプス学習を実装すること
JP2016538633A (ja) 多次元範囲にわたって分離可能なサブシステムを含むシステムの評価
JP2017510890A (ja) 一般的なニューロンモデルの効率的な実装のための方法および装置
US9710749B2 (en) Methods and apparatus for implementing a breakpoint determination unit in an artificial nervous system
JP6193509B2 (ja) 可塑性シナプス管理
JP6219509B2 (ja) シナプス遅延を動的に割り当てることおおよび検査すること
US9418332B2 (en) Post ghost plasticity
JP6096388B2 (ja) ニューラルネットワークモデルにおけるドップラー効果処理
JP2016536676A (ja) ニューラルモデル実行をリモートで制御および監視するための方法および装置
US20150278684A1 (en) Time synchronization of spiking neuron models on multiple nodes

Legal Events

Date Code Title Description
A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20160906

A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20171121

A621 Written request for application examination

Free format text: JAPANESE INTERMEDIATE CODE: A621

Effective date: 20171121

A977 Report on retrieval

Free format text: JAPANESE INTERMEDIATE CODE: A971007

Effective date: 20181016

A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20181023

A02 Decision of refusal

Free format text: JAPANESE INTERMEDIATE CODE: A02

Effective date: 20190521