FINITE RING NEURAL NETWORK Russian patent published in 2019 - IPC G06N3/04 G06N3/02 

Abstract RU 2701064 C1

FIELD: information technology.

SUBSTANCE: invention relates to neural networks of a finite ring. Final ring neuron network for classifying numbers by a given module p comprises an output layer for storing a number presented in a positional number system, concealed layer of neurons intended for weighted summation of stored numbers and output layer intended to generate their inputs of residues of number z on selected modulus p of summation, wherein outputs of neurons of input layer are connected to inputs of hidden layer neurons, connected in pairs to each other, outputs of concealed layer neurons are connected to inputs of output layer neurons, wherein the network includes first and second registers, a group of AND units, wherein the input code of the source number information input is connected to the first register information input, the device calculation start input is connected to the first and second registers entry inputs, and the second register zero-information input is connected to recording input of second register.

EFFECT: higher reliability of neurocomputer equipment.

1 cl, 1 dwg

Similar patents RU2701064C1

Title Year Author Number
FINITE RING NEURAL NETWORK 2020
  • Irkhin Valerij Petrovich
  • Melnik Vyacheslav Aleksandrovich
  • Erofeev Andrej Nikolaevich
  • Berezin Aleksandr Yurevich
  • Telegin Evgenij Nikolaevich
RU2759964C1
NEURON NETWORK OF FINITE RING 2003
  • Chervjakov Nikolaj Ivanovich
  • Galkina Valentina Andreevna
  • Strekalov Jurij Anatol'Evich
  • Lavrinenko Sergej Viktorovich
RU2279132C2
NEURON NETWORK OF ACCELERATED RANGING OF MODULAR NUMBERS 2007
  • Chervjakov Nikolaj Ivanovich
  • Golovko Aleksandr Nikolaevich
  • Lavrinenko Anton Viktorovich
  • Sljadnev Vitalij Viktorovich
RU2359325C2
RELIABLE CLOUD STORAGE SYSTEM WITH ADJUSTABLE DATA REDUNDANCY 2021
  • Babenko Mikhail Grigorevich
  • Kuchukov Viktor Andreevich
  • Kucherov Nikolai Nikolaevich
  • Gladkov Andrei Vladimirovich
RU2782681C1
PARALLEL ADDER-SUBTRACTOR IN TERNARY NUMBER SYSTEM ON NEURONS 2010
  • Shevelev Sergej Stepanovich
RU2453900C2
APPARATUS FOR CONVERTING BINARY CODE TO RESIDUE NUMBER SYSTEM (RNS) CODE 2009
  • Ljubomudrov Aleksej Alekseevich
RU2413279C1
NEURAL NETWORK WITH THRESHOLD (k, t) STRUCTURE FOR RESIDUAL CODE - BINARY POSITION CODE CONVERSION 2008
  • Chervjakov Nikolaj Ivanovich
  • Golovko Aleksandr Nikolaevich
  • Lavrinenko Anton Viktorovich
  • Kondrashov Jurij Vladimirovich
  • Kozlov Vladimir Andreevich
  • Nazarenko Sergej Vasil'Evich
  • Ospishchev Mikhail Aleksandrovich
RU2380751C1
NEURON-BASED RIPPLE CARRY PARALLEL ADDER-SUBTRACTOR 2012
  • Shevelev Sergej Stepanovich
  • Solodovnikov Fedor Mikhajlovich
  • Shikunov Dmitrij Aleksandrovich
  • Shikunova Elena Sergeevna
  • Khla Vin
RU2523942C2
NEURON NETWORK FOR TRANSFORMATION OF RESIDUAL CODE TO BINARY POSITIONAL CODE 2006
  • Chervjakov Nikolaj Ivanovich
RU2318238C1
DEVICE FOR PRIMARY DIVISION OF MOLECULAR NUMBERS 2013
  • Chervjakov Nikolaj Ivanovich
  • Babenko Mikhail Grigor'Evich
  • Ljakhov Pavel Alekseevich
  • Lavrinenko Irina Nikolaevna
RU2559771C2

RU 2 701 064 C1

Authors

Dolgachev Aleksandr Aleksandrovich

Irkhin Valerij Petrovich

Andreev Roman Nikolaevich

Melnik Vyacheslav Aleksandrovich

Dates

2019-09-24Published

2018-09-20Filed