NEAR-REAL IMPULSE NEURON Russian patent published in 2016 - IPC G06N3/06 G06G7/60 

Abstract RU 2598298 C2

FIELD: neurons simulation.

SUBSTANCE: invention can be used on the neural computers, in the technical systems based on neural networks for pattern recognition, analysis and processing of the images. Device comprises inputs for impulse flows, interconnection links, cluster made of part of the input connection links; cluster is formed from the input connection links depending on the structure of periods and localisation of partial impulse flows at the neuron input, that implements existence for total impulse flow at the output of the cluster ε-almost-periods with maximum sum of amplitudes of all partial impulse flows; impulse flow from the output of the cluster is fed to the adder, which is associated with a liminal excitable element which generates an output impulse sequence or single impulse at exceeding of amplitude of impulse flows at the output of the adder liminal excitable element by the maximum sum; signal from the output of liminal excitable element is used as the output one.

EFFECT: technical result is provision of an opportunity to achieve selective detection of the input objects without using a balance measurement of the input signals, possibility of encoding the input object of a certain type by the channel number or by the number of recording neuron, compression of input information, performance increase, objects recognition reliability increase.

1 cl, 9 dwg, 2 tbl

Similar patents RU2598298C2

Title Year Author Number
SINGLE-LAYER PERCEPTRON, SIMULATING REAL PERCEPTRON PROPERTIES 2015
  • Mazurov Mikhail Efimovich
RU2597496C1
SINGLE-LAYER PERCEPTRON BASED ON SELECTIVE NEURONS 2015
  • Mazurov Mikhail Efimovich
RU2597497C2
NEURON SIMULATION OF REAL NEURON PROPERTIES 2014
  • Mazurov Mikhail Efimovich
RU2597495C2
INFORMATION ENCODING METHOD IN PULSED NEURAL NETWORKS 2019
  • Mazurov Mikhail Efimovich
RU2748257C2
INSTRUMENTAL METHOD OF TRAINING SELECTIVE NEURAL NETWORK WITHOUT MATHEMATICS AND WITHOUT A TEACHER WITH USE OF SELF-ORGANIZATION 2019
  • Mazurov Mikhail Efimovich
RU2729878C2
NEURON MODEL BASED ON DENDRITIC COMPUTING 2021
  • Vityaev Evgenii Evgenevich
RU2777262C1
EFFECTIVE PERCEPTRON BASED ON MCCULLOCH-PITTS NEURONS USING COMPARATORS 2019
  • Mazurov Mikhail Efimovich
  • Egisapetov Eduard Grigorevich
  • Markovskij Stanislav Nikolaevich
RU2729554C1
DEVICE FOR SIMULATING NEURON 1991
  • Zhukov A.G.
  • Lavrova T.S.
  • Savel'Ev A.V.
RU2028669C1
NEURON SIMULATOR 0
  • Saveleva Nina Andreevna
  • Savelev Aleksandr Viktorovich
  • Kolesnikov Andrej Aleksandrovich
  • Zhukov Anatolij Geralevich
SU1501101A1
METHOD AND DEVICE FOR NEURAL TIME CODING, TRAINING AND RECOGNITION 2012
  • Chen Viktor Khokkyu
  • Khanzindzher Dzhejson Frenk
  • Bekhabadi Bardia Fallakh
RU2597504C2

RU 2 598 298 C2

Authors

Mazurov Mikhail Efimovich

Dates

2016-09-20Published

2015-02-09Filed