RU94045146A - Нейронная сеть и способ ее функционирования - Google Patents

Нейронная сеть и способ ее функционирования

Info

Publication number
RU94045146A
RU94045146A RU94045146/09A RU94045146A RU94045146A RU 94045146 A RU94045146 A RU 94045146A RU 94045146/09 A RU94045146/09 A RU 94045146/09A RU 94045146 A RU94045146 A RU 94045146A RU 94045146 A RU94045146 A RU 94045146A
Authority
RU
Russia
Prior art keywords
neutron
circuit
neutrons
facility
neutron circuit
Prior art date
Application number
RU94045146/09A
Other languages
English (en)
Inventor
Томас Ванг Шай-Пинг
Us]
Original Assignee
Моторола
Моторола, Инк.
Инк. (US)
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 Моторола, Моторола, Инк., Инк. (US) filed Critical Моторола
Publication of RU94045146A publication Critical patent/RU94045146A/ru

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Theoretical Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Computational Linguistics (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Neurology (AREA)
  • Feedback Control In General (AREA)
  • Image Analysis (AREA)
  • Devices For Executing Special Programs (AREA)
  • Measurement Of Radiation (AREA)

Abstract

Нейронная сеть, которая может быть реализована аппаратным либо программным способами, построена на нейронах или нейронных схемах, каждая из которых имеет обрабатывающий элемент в виде сумматора. Каждая нейронная сеть, кроме того, включает средство 4 для приложения логарифмической функции к ее входным сигналам (х-х) и средство 12 для приложения обратной логарифмической функции к выходным сигналам ее нейронов 5-8. Нейронная сеть использует алгоритм обучения, который не требует повторного обучения и вырабатывает глобальный минимум для каждого заданного набора входных векторов.

Claims (1)

  1. Нейронная сеть, которая может быть реализована аппаратным либо программным способами, построена на нейронах или нейронных схемах, каждая из которых имеет обрабатывающий элемент в виде сумматора. Каждая нейронная сеть, кроме того, включает средство 4 для приложения логарифмической функции к ее входным сигналам (х1-хn) и средство 12 для приложения обратной логарифмической функции к выходным сигналам ее нейронов 5-8. Нейронная сеть использует алгоритм обучения, который не требует повторного обучения и вырабатывает глобальный минимум для каждого заданного набора входных векторов.
    Figure 00000001
RU94045146/09A 1994-01-03 1994-12-29 Нейронная сеть и способ ее функционирования RU94045146A (ru)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US17660194A 1994-01-03 1994-01-03
US08/176601 1994-01-03

Publications (1)

Publication Number Publication Date
RU94045146A true RU94045146A (ru) 1996-10-20

Family

ID=22645042

Family Applications (2)

Application Number Title Priority Date Filing Date
RU94045263/09A RU94045263A (ru) 1994-01-03 1994-12-29 Искусственная нейронная схема и использованный в ней способ формирования выходного сигнала
RU94045146/09A RU94045146A (ru) 1994-01-03 1994-12-29 Нейронная сеть и способ ее функционирования

Family Applications Before (1)

Application Number Title Priority Date Filing Date
RU94045263/09A RU94045263A (ru) 1994-01-03 1994-12-29 Искусственная нейронная схема и использованный в ней способ формирования выходного сигнала

Country Status (7)

Country Link
US (1) US5778153A (ru)
EP (1) EP0661645A3 (ru)
JP (1) JPH07210534A (ru)
KR (1) KR950024083A (ru)
CA (1) CA2135857A1 (ru)
RU (2) RU94045263A (ru)
TW (1) TW386198B (ru)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
RU2459254C2 (ru) * 2007-04-27 2012-08-20 Сименс Акциенгезелльшафт Способ компьютеризованного обучения одной или более нейронных сетей
CN110383301A (zh) * 2017-03-08 2019-10-25 阿姆有限公司 尖峰神经网络

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6501805B1 (en) 1999-05-14 2002-12-31 Harris Corporation Broadcast transmission system with single correction filter for correcting linear and non-linear distortion
US11244225B2 (en) * 2015-07-10 2022-02-08 Samsung Electronics Co., Ltd. Neural network processor configurable using macro instructions
CN106777829B (zh) * 2017-02-06 2019-04-12 深圳晶源信息技术有限公司 一种集成电路掩模设计的优化方法及计算机可读的存储介质
US10929746B2 (en) * 2017-11-27 2021-02-23 Samsung Electronics Co., Ltd. Low-power hardware acceleration method and system for convolution neural network computation
WO2019155910A1 (ja) * 2018-02-06 2019-08-15 国立大学法人北海道大学 ニューラル電子回路
DE102019208257A1 (de) * 2018-07-03 2020-01-09 Heidelberger Druckmaschinen Ag Druckqualitätsanalyse mit neuronalen Netzen
JP2020188386A (ja) * 2019-05-15 2020-11-19 ソニーセミコンダクタソリューションズ株式会社 固体撮像装置及び電子機器

Family Cites Families (29)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US3551663A (en) * 1965-04-15 1970-12-29 Gen Electric Multiplication apparatus in a data processing system with a variable length multiplier
US3748451A (en) * 1970-08-21 1973-07-24 Control Data Corp General purpose matrix processor with convolution capabilities
FR2212952A5 (ru) * 1972-12-29 1974-07-26 Cit Alcatel
US3967100A (en) * 1973-11-12 1976-06-29 Naonobu Shimomura Digital function generator utilizing cascade accumulation
US3922536A (en) * 1974-05-31 1975-11-25 Rca Corp Multionomial processor system
PL106470B1 (pl) * 1977-02-01 1979-12-31 Inst Maszyn Matematycznych Uklad cyfrowy do obliczania wartosci zlozonych wyrazen arytmetycznych
DE3506749A1 (de) * 1984-02-27 1985-09-26 Nippon Telegraph & Telephone Public Corp., Tokio/Tokyo Matrixprozessor und steuerverfahren hierfuer
US4626825A (en) * 1985-07-02 1986-12-02 Vlsi Technology, Inc. Logarithmic conversion apparatus
US5109524A (en) * 1985-07-02 1992-04-28 Vlsi Technology, Inc. Digital processor with a four part data register for storing data before and after data conversion and data calculations
GB8619452D0 (en) * 1986-08-08 1986-12-17 Dobson V G Signal generating & processing
JPH077389B2 (ja) * 1987-05-14 1995-01-30 富士通株式会社 再帰方程式を高速で処理するベクトル処理装置
US5337266A (en) * 1987-12-21 1994-08-09 Arnold Mark G Method and apparatus for fast logarithmic addition and subtraction
US4849925A (en) * 1988-01-15 1989-07-18 The United States Of America As Represented By The Secretary Of The Navy Maximum entropy deconvolver circuit based on neural net principles
FI894021A (fi) * 1988-08-31 1990-03-01 Fujitsu Ltd Neuronstruktur.
US5073867A (en) * 1989-06-12 1991-12-17 Westinghouse Electric Corp. Digital neural network processing elements
US5359551A (en) * 1989-06-14 1994-10-25 Log Point Technologies, Inc. High speed logarithmic function generating apparatus
US5113367A (en) * 1989-07-03 1992-05-12 The United States Of America As Represented By The Secretary Of The Navy Cross entropy deconvolver circuit adaptable to changing convolution functions
US5042001A (en) * 1989-10-02 1991-08-20 Cyrix Corporation Method and apparatus for performing mathematical functions using polynomial approximation and a rectangular aspect ratio multiplier
US5068816A (en) * 1990-02-16 1991-11-26 Noetzel Andrew S Interplating memory function evaluation
US5343254A (en) * 1991-04-25 1994-08-30 Olympus Optical Co., Ltd. Image signal processing device capable of suppressing nonuniformity of illumination
JP3003276B2 (ja) * 1991-06-19 2000-01-24 松下電器産業株式会社 信号解析装置
US5450522A (en) * 1991-08-19 1995-09-12 U S West Advanced Technologies, Inc. Auditory model for parametrization of speech
US5331582A (en) * 1991-12-16 1994-07-19 Pioneer Electronic Corporation Digital signal processor using a coefficient value corrected according to the shift of input data
US5365465A (en) * 1991-12-26 1994-11-15 Texas Instruments Incorporated Floating point to logarithm converter
US5278945A (en) * 1992-01-10 1994-01-11 American Neuralogical, Inc. Neural processor apparatus
ATE168481T1 (de) * 1992-02-29 1998-08-15 Bernd Hoefflinger Schaltungsanordnung zum digitalen multiplizieren von integer-zahlen
JPH05342191A (ja) * 1992-06-08 1993-12-24 Mitsubishi Electric Corp 経済時系列データ予測及び解析システム
US5517667A (en) * 1993-06-14 1996-05-14 Motorola, Inc. Neural network that does not require repetitive training
US5553012A (en) * 1995-03-10 1996-09-03 Motorola, Inc. Exponentiation circuit utilizing shift means and method of using same

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
RU2459254C2 (ru) * 2007-04-27 2012-08-20 Сименс Акциенгезелльшафт Способ компьютеризованного обучения одной или более нейронных сетей
CN110383301A (zh) * 2017-03-08 2019-10-25 阿姆有限公司 尖峰神经网络
CN110383301B (zh) * 2017-03-08 2023-09-05 阿姆有限公司 尖峰神经网络

Also Published As

Publication number Publication date
CA2135857A1 (en) 1995-07-04
RU94045263A (ru) 1996-10-20
JPH07210534A (ja) 1995-08-11
EP0661645A2 (en) 1995-07-05
TW386198B (en) 2000-04-01
US5778153A (en) 1998-07-07
KR950024083A (ko) 1995-08-21
EP0661645A3 (en) 1995-09-20

Similar Documents

Publication Publication Date Title
Schiller Quasi-classical theory of the nonspinning electron
RU94045146A (ru) Нейронная сеть и способ ее функционирования
Schoech Human Services Computing.
MY123725A (en) Method and device for local contrast enhancement of video signal
Rahimian et al. Digital implementation of the two-compartmental Pinsky–Rinzel pyramidal neuron model
Gutierrez-Galan et al. An event-based digital time difference encoder model implementation for neuromorphic systems
KR920007504B1 (ko) 신경회로망을 이용한 이진 가산기
Hopfield The effectiveness of analogue'neural network'hardware
Gürbüz Sublinear operators with rough kernel generated by Calderón–Zygmund operators and their commutators on generalized Morrey spaces
Yao et al. Periodic solutions to impulsive stochastic reaction-diffusion neural networks with delays
Hoshiya et al. Simulation methods of multi-dimensional nonstationary stochastic processes by time domain models
Jahnke et al. Towards efficient hardware for spike-processing neural networks
Jain et al. High-speed double precision computation of nonlinear functions
Davies The boundary element method on the ICL DAP
Bendat Exact integral equation solutions and synthesis for a large class of optimum time variable linear filters
Molley Implementing the difference-squared error algorithm using an acousto-optic processor
Roska AnaLogic wave computers-wave-type algorithms: canonical description, computer classes, and computational complexity
Dempsey et al. A Hough transform system based on neural networks
Haneveld et al. Escape time for a random walk from an orthant
Park Hopfield neural network for AR spectral estimator
Vijaya Certain subclass of Pascu-type bi-starlike functions in parabolic domain
Wang Analog CMOS implementation of backward error propagation
Kouhara et al. Learning algorithm based on moderationism for multi-layer neural networks
Vincent et al. Parameter selection for digital realisations of neural networks
ATE227860T1 (de) Assoziativneuron in einem künstlichen neuralen netzwerk