CN120542480A - 脉冲神经网络 - Google Patents

脉冲神经网络

Info

Publication number
CN120542480A
CN120542480A CN202510624575.9A CN202510624575A CN120542480A CN 120542480 A CN120542480 A CN 120542480A CN 202510624575 A CN202510624575 A CN 202510624575A CN 120542480 A CN120542480 A CN 120542480A
Authority
CN
China
Prior art keywords
stage
input
output
pulse
spatiotemporal
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
CN202510624575.9A
Other languages
English (en)
Chinese (zh)
Inventor
S·S·库马尔
A·齐亚约
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.)
Innatra Nano Systems Co ltd
Original Assignee
Innatra Nano Systems Co ltd
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 Innatra Nano Systems Co ltd filed Critical Innatra Nano Systems Co ltd
Publication of CN120542480A publication Critical patent/CN120542480A/zh
Pending legal-status Critical Current

Links

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
    • G06N3/045—Combinations of 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
    • G06N3/04—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
    • G06N3/06—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
    • 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
    • G06N3/088—Non-supervised learning, e.g. competitive learning
    • 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)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • General Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Computational Linguistics (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Neurology (AREA)
  • Image Analysis (AREA)
  • Feedback Control In General (AREA)
CN202510624575.9A 2018-11-18 2019-11-14 脉冲神经网络 Pending CN120542480A (zh)

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
US201862768927P 2018-11-18 2018-11-18
US62/768,927 2018-11-18
CN201980088638.6A CN113287122B (zh) 2018-11-18 2019-11-14 脉冲神经网络
PCT/EP2019/081373 WO2020099583A1 (en) 2018-11-18 2019-11-14 Spiking neural network

Related Parent Applications (1)

Application Number Title Priority Date Filing Date
CN201980088638.6A Division CN113287122B (zh) 2018-11-18 2019-11-14 脉冲神经网络

Publications (1)

Publication Number Publication Date
CN120542480A true CN120542480A (zh) 2025-08-26

Family

ID=68583418

Family Applications (4)

Application Number Title Priority Date Filing Date
CN202510624575.9A Pending CN120542480A (zh) 2018-11-18 2019-11-14 脉冲神经网络
CN201980088638.6A Active CN113287122B (zh) 2018-11-18 2019-11-14 脉冲神经网络
CN202510680826.5A Pending CN120494009A (zh) 2018-11-18 2019-11-18 弹性神经网络
CN201980084907.1A Active CN113272828B (zh) 2018-11-18 2019-11-18 弹性神经网络

Family Applications After (3)

Application Number Title Priority Date Filing Date
CN201980088638.6A Active CN113287122B (zh) 2018-11-18 2019-11-14 脉冲神经网络
CN202510680826.5A Pending CN120494009A (zh) 2018-11-18 2019-11-18 弹性神经网络
CN201980084907.1A Active CN113272828B (zh) 2018-11-18 2019-11-18 弹性神经网络

Country Status (6)

Country Link
US (3) US20220230051A1 (https=)
EP (2) EP3881241A1 (https=)
JP (4) JP7562522B2 (https=)
KR (2) KR20210124960A (https=)
CN (4) CN120542480A (https=)
WO (2) WO2020099583A1 (https=)

Families Citing this family (36)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102744306B1 (ko) * 2018-12-07 2024-12-18 삼성전자주식회사 뉴럴 네트워크를 분할하는 방법 및 뉴로모픽 장치
US20200293860A1 (en) * 2019-03-11 2020-09-17 Infineon Technologies Ag Classifying information using spiking neural network
US11468276B2 (en) * 2020-04-16 2022-10-11 Robert Bosch Gmbh System and method of a monotone operator neural network
CN111723726B (zh) * 2020-06-17 2023-09-19 苏州大学 一种脉冲神经膜系统干燥剂包装袋识别模型的识别方法
US12347421B2 (en) * 2020-06-25 2025-07-01 PolyN Technology Limited Sound signal processing using a neuromorphic analog signal processor
US20210406661A1 (en) 2020-06-25 2021-12-30 PolyN Technology Limited Analog Hardware Realization of Neural Networks
US20230368004A1 (en) * 2020-10-05 2023-11-16 Innatera Nanosystems B.V. Adaptation of snns through transient synchrony
US20220156564A1 (en) * 2020-11-18 2022-05-19 Micron Technology, Inc. Routing spike messages in spiking neural networks
KR102558169B1 (ko) * 2020-11-20 2023-07-24 한국과학기술원 신경 발화 데이터 프로파일링 및 컨텐츠 추출을 위한 컴퓨터 시스템, 및 그의 방법
KR20220081782A (ko) 2020-12-09 2022-06-16 삼성전자주식회사 뉴럴 네트워크를 이용하는 데이터 처리 방법, 데이터 처리 장치 및 이를 포함한 전자 장치
JP7438994B2 (ja) * 2021-01-07 2024-02-27 株式会社東芝 ニューラルネットワーク装置及び学習方法
EP4535238A3 (en) * 2021-04-16 2025-06-25 Innatera Nanosystems B.V. Hierarchical reconfigurable multi-segment spiking neural network
CN117203946A (zh) * 2021-04-16 2023-12-08 诺基亚通信公司 用于确定随机接入前导标识符的装置、方法和非瞬态计算机可读介质
US20230004777A1 (en) * 2021-07-05 2023-01-05 Electronics And Telecommunications Research Institute Spike neural network apparatus based on multi-encoding and method of operation thereof
SE2151099A1 (en) * 2021-09-03 2023-03-04 IntuiCell AB A computer-implemented or hardware-implemented method, a computer program product, an apparatus, a transfer function unit and a system for identification or separation of entities
US12001529B1 (en) * 2021-11-05 2024-06-04 Validate Me LLC Counting machine for manufacturing and validating event-relevant identities via an ensemble network
CN116245147B (zh) * 2021-12-03 2025-12-05 中国科学院微电子研究所 一种脉冲神经网络结构
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
CN114781597B (zh) * 2022-03-28 2024-09-06 华中科技大学 面向时间序列预测的漂移脉冲神经网络构建方法及其应用
CN114781575B (zh) * 2022-04-07 2025-04-08 华南师范大学 一种基于秀丽线虫神经元的全智能小车
KR102845414B1 (ko) * 2022-05-30 2025-08-12 한국전자통신연구원 스파이크 뉴럴 네트워크 회로
US12579470B2 (en) 2022-06-24 2026-03-17 Microsoft Technology Licensing, Llc Systems and methods for distributing layers of special mixture-of-experts machine learning models
EP4303766A1 (en) * 2022-07-07 2024-01-10 Centre national de la recherche scientifique A neuro-synaptic system for real time processing of trading data and associated computer program
CN115496195A (zh) * 2022-08-08 2022-12-20 西安电子科技大学 基于mzi阵列和fp-sa的光脉冲神经网络实现装置
KR20250051711A (ko) * 2022-08-16 2025-04-17 인나테라 나노시스템즈 비.브이. 재구성 가능한 모듈형 뉴로시냅틱 연산 구조를 위한 시스템 및 방법
US20240086682A1 (en) * 2022-09-13 2024-03-14 International Business Machines Corporation Function-based activation of memory tiers
CN115421929A (zh) * 2022-11-04 2022-12-02 北京大学 MoE模型训练方法、装置、设备以及存储介质
EP4369032A1 (en) * 2022-11-09 2024-05-15 VoxelSensors SRL Optical sensing system
US20240221756A1 (en) * 2022-12-29 2024-07-04 Intel Corporation End-to-end neuromorphic acoustic processing
CN116757256B (zh) * 2023-06-06 2026-02-13 深圳时识科技有限公司 带通滤波方法及装置、芯片及电子设备
CN117077746B (zh) * 2023-08-25 2025-08-05 南京大学 基于二值权重的脉冲神经网络的无监督片上学习系统
US20250232162A1 (en) * 2024-01-16 2025-07-17 Huawei Technologies Co., Ltd. Method and apparatus for improved generative ai models
CN117688992B (zh) * 2024-02-01 2024-06-04 之江实验室 神经元计算机操作系统的资源映射方法和装置
CN118096500B (zh) * 2024-03-15 2024-09-13 山东科技大学 基于多稳态耦合神经网络动力学特性的图像储存方法及系统
KR102945523B1 (ko) * 2024-10-04 2026-03-30 고려대학교 세종산학협력단 단기 기억 시냅스 소자를 활용한 대역 통과 필터
CN120134326B (zh) * 2025-05-13 2025-07-15 江苏智慧工场技术研究院有限公司 一种控制双轮机器人直线行走的方法和系统

Family Cites Families (46)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2810202B2 (ja) 1990-04-25 1998-10-15 株式会社日立製作所 ニューラルネットワークによる情報処理装置
JP3560670B2 (ja) * 1995-02-06 2004-09-02 富士通株式会社 適応的認識システム
US8606732B2 (en) * 2010-08-04 2013-12-10 Qualcomm Incorporated Methods and systems for reward-modulated spike-timing-dependent-plasticity
US8942466B2 (en) * 2010-08-26 2015-01-27 Brain Corporation Sensory input processing apparatus and methods
US20120084240A1 (en) * 2010-09-30 2012-04-05 International Business Machines Corporation Phase change memory synaptronic circuit for spiking computation, association and recall
US8515885B2 (en) * 2010-10-29 2013-08-20 International Business Machines Corporation Neuromorphic and synaptronic spiking neural network with synaptic weights learned using simulation
US8856055B2 (en) * 2011-04-08 2014-10-07 International Business Machines Corporation Reconfigurable and customizable general-purpose circuits for neural networks
US9047568B1 (en) * 2012-09-20 2015-06-02 Brain Corporation Apparatus and methods for encoding of sensory data using artificial spiking neurons
US9147156B2 (en) * 2011-09-21 2015-09-29 Qualcomm Technologies Inc. Apparatus and methods for synaptic update in a pulse-coded network
US9460387B2 (en) * 2011-09-21 2016-10-04 Qualcomm Technologies Inc. Apparatus and methods for implementing event-based updates in neuron networks
US8725662B2 (en) * 2011-09-21 2014-05-13 Brain Corporation Apparatus and method for partial evaluation of synaptic updates based on system events
US9159020B2 (en) 2012-09-14 2015-10-13 International Business Machines Corporation Multiplexing physical neurons to optimize power and area
US9189730B1 (en) * 2012-09-20 2015-11-17 Brain Corporation Modulated stochasticity spiking neuron network controller apparatus and methods
JP5284530B2 (ja) 2012-11-22 2013-09-11 キヤノン株式会社 情報処理方法、情報処理装置
EP2973240A4 (en) * 2013-03-15 2017-09-27 HRL Laboratories, LLC Neural network and method of programming
US9558443B2 (en) * 2013-08-02 2017-01-31 International Business Machines Corporation Dual deterministic and stochastic neurosynaptic core circuit
US10095718B2 (en) * 2013-10-16 2018-10-09 University Of Tennessee Research Foundation Method and apparatus for constructing a dynamic adaptive neural network array (DANNA)
US20150120627A1 (en) 2013-10-29 2015-04-30 Qualcomm Incorporated Causal saliency time inference
US20150170027A1 (en) * 2013-12-13 2015-06-18 Qualcomm Incorporated Neuronal diversity in spiking neural networks and pattern classification
US20150242745A1 (en) * 2014-02-21 2015-08-27 Qualcomm Incorporated Event-based inference and learning for stochastic spiking bayesian networks
US20150269485A1 (en) * 2014-03-24 2015-09-24 Qualcomm Incorporated Cold neuron spike timing back-propagation
US10006978B2 (en) * 2014-05-30 2018-06-26 Leidos Innovations Technology, Inc. Method and system for signal processing
US9990580B2 (en) 2015-03-13 2018-06-05 International Business Machines Corporation Neuromorphic synapses
EP3271872A4 (en) * 2015-03-18 2018-12-05 Hrl Laboratories, Llc System and method for decoding spiking reservoirs with continuous synaptic plasticity
US9971965B2 (en) * 2015-03-18 2018-05-15 International Business Machines Corporation Implementing a neural network algorithm on a neurosynaptic substrate based on metadata associated with the neural network algorithm
US9984323B2 (en) * 2015-03-26 2018-05-29 International Business Machines Corporation Compositional prototypes for scalable neurosynaptic networks
CN106250981B (zh) * 2015-06-10 2022-04-01 三星电子株式会社 减少存储器访问和网络内带宽消耗的脉冲神经网络
US11157800B2 (en) * 2015-07-24 2021-10-26 Brainchip, Inc. Neural processor based accelerator system and method
KR20170025715A (ko) * 2015-08-31 2017-03-08 에스케이하이닉스 주식회사 시냅스 및 이를 포함하는 뉴로모픽 장치
US10733500B2 (en) * 2015-10-21 2020-08-04 International Business Machines Corporation Short-term memory using neuromorphic hardware
CN105404902B (zh) * 2015-10-27 2019-02-05 清华大学 基于脉冲神经网络的图像特征描述和记忆方法
US10460237B2 (en) * 2015-11-30 2019-10-29 International Business Machines Corporation Neuron-centric local learning rate for artificial neural networks to increase performance, learning rate margin, and reduce power consumption
CN105719000B (zh) * 2016-01-21 2018-02-16 广西师范大学 一种神经元硬件装置及用这种装置模拟脉冲神经网络的方法
US11157798B2 (en) * 2016-02-12 2021-10-26 Brainchip, Inc. Intelligent autonomous feature extraction system using two hardware spiking neutral networks with spike timing dependent plasticity
US20170236027A1 (en) 2016-02-16 2017-08-17 Brainchip Inc. Intelligent biomorphic system for pattern recognition with autonomous visual feature extraction
KR102399548B1 (ko) * 2016-07-13 2022-05-19 삼성전자주식회사 뉴럴 네트워크를 위한 방법 및 그 방법을 수행하는 장치
US10671912B2 (en) * 2016-09-13 2020-06-02 Sap Se Spatio-temporal spiking neural networks in neuromorphic hardware systems
US10338629B2 (en) * 2016-09-22 2019-07-02 International Business Machines Corporation Optimizing neurosynaptic networks
EP3324343A1 (en) * 2016-11-21 2018-05-23 Centre National de la Recherche Scientifique Unsupervised detection of repeating patterns in a series of events
US10885425B2 (en) * 2016-12-20 2021-01-05 Intel Corporation Network traversal using neuromorphic instantiations of spike-time-dependent plasticity
US11151441B2 (en) * 2017-02-08 2021-10-19 Brainchip, Inc. System and method for spontaneous machine learning and feature extraction
CN107092959B (zh) * 2017-04-07 2020-04-10 武汉大学 基于stdp非监督学习算法的脉冲神经网络模型构建方法
US10878313B2 (en) * 2017-05-02 2020-12-29 Intel Corporation Post synaptic potential-based learning rule
US20200272883A1 (en) * 2017-12-19 2020-08-27 Intel Coporation Reward-based updating of synpatic weights with a spiking neural network
US11423312B2 (en) * 2018-05-14 2022-08-23 Samsung Electronics Co., Ltd Method and apparatus for universal pruning and compression of deep convolutional neural networks under joint sparsity constraints
WO2020049541A1 (en) * 2018-09-09 2020-03-12 Gore Mihir Ratnakar A neuromorphic computing system

Also Published As

Publication number Publication date
US12380320B2 (en) 2025-08-05
JP2022507721A (ja) 2022-01-18
EP3881246A2 (en) 2021-09-22
WO2020099680A2 (en) 2020-05-22
JP7520829B2 (ja) 2024-07-23
CN113287122B (zh) 2025-06-06
CN113272828A (zh) 2021-08-17
US20220230051A1 (en) 2022-07-21
JP7562522B2 (ja) 2024-10-07
JP2022509618A (ja) 2022-01-21
JP2025013779A (ja) 2025-01-28
US20260017500A1 (en) 2026-01-15
WO2020099680A3 (en) 2020-07-23
WO2020099583A1 (en) 2020-05-22
JP2024160227A (ja) 2024-11-13
KR20210127133A (ko) 2021-10-21
KR20210124960A (ko) 2021-10-15
CN113287122A (zh) 2021-08-20
CN120494009A (zh) 2025-08-15
CN113272828B (zh) 2025-06-17
EP3881241A1 (en) 2021-09-22
US20220012564A1 (en) 2022-01-13

Similar Documents

Publication Publication Date Title
CN113287122B (zh) 脉冲神经网络
Wang et al. Neuromorphic hardware architecture using the neural engineering framework for pattern recognition
CN113313240B (zh) 计算设备及电子设备
US20180247199A1 (en) Method and apparatus for multi-dimensional sequence prediction
US20200265301A1 (en) Incremental training of machine learning tools
Dai Real-time and accurate object detection on edge device with TensorFlow Lite
JP2017516192A (ja) ニューラルネットワークにおける差分符号化
Lemaire et al. An fpga-based hybrid neural network accelerator for embedded satellite image classification
CN113628615B (zh) 语音识别方法、装置、电子设备及存储介质
CN116663623B (zh) 类脑突触学习方法及类脑技术的神经形态硬件系统
Liu et al. Bird song classification based on improved Bi-LSTM-DenseNet network
CN114545354A (zh) 一种海面目标分类方法及系统
CN115762478B (zh) 基于光子脉冲神经网络的语音识别方法
CN114943330A (zh) 一种神经网络模型的训练方法、装置、设备及存储介质
CN115114411A (zh) 基于知识图谱的预测方法、装置和电子设备
Cai et al. Spike timing dependent gradient for direct training of fast and efficient binarized spiking neural networks
Habib et al. Enhanced protonet with self-knowledge distillation for few-shot learning
Frid et al. Temporal pattern recognition via temporal networks of temporal neurons
Wu et al. Practical Guidelines for Spiking Neural Networks
US20230351165A1 (en) Method for operating neural network
EP4604014A1 (en) Neural network architecture
Basu et al. Fundamental Survey on Neuromorphic Based Audio Classification
US20250146861A1 (en) Unsupervised transformer signal separation
US20240346296A1 (en) Low-latency time-encoded spiking neural network
CN121902886A (zh) 数字脉冲神经元、脉冲神经网络及其实现方法

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination