NEURON SIMULATION METHOD Russian patent published in 2010 - IPC G06N3/06 

Abstract RU 2402813 C1

FIELD: physics.

SUBSTANCE: neuron simulation method is based on calculation of squares of Euclidean distance from the input vector to each of 2n vertices of a unit n-dimensional cube in weighting units, and multiplication of values inverse to these distance values with components of the target vector respectively, and then summation in an adder and conversion in the activation unit through an activation function.

EFFECT: possibility of simulating a neuron of any given Boolean function from a complete set of from n variables.

6 dwg, 1 tbl

Similar patents RU2402813C1

Title Year Author Number
METHOD FOR REALIZING LOGICAL NONEQUIVALENCE FUNCTION BY A NEURON 2006
  • Samojlin Evgenij Aleksandrovich
RU2308758C1
CONTROL METHOD OF NEUROPROCESSOR RESPONSE TO INPUT SIGNALS 2018
  • Dembitskij Nikolaj Leonidovich
RU2724784C2
NEURON MODEL, REALIZING LOGICAL NONEQUIVALENCE FUNCTION 2003
  • Samojlin Evgenij Aleksandrovich
RU2269155C2
METHOD OF TRAINING ARTIFICIAL NEURAL NETWORK 2014
  • Sal'Nikov Vladimir Sergeevich
  • Khoang Van Chi
  • Antsev Aleksandr Vital'Evich
RU2566979C1
METHOD OF NOISE-IMMUNE GRADIENT DETECTION OF CONTOURS OF OBJECTS ON DIGITAL IMAGES 2008
  • Samojlin Evgenij Aleksandrovich
RU2360289C1
SELF-CHECKING MODULAR COMPUTER OF BOOLEAN FUNCTION SYSTEMS 2009
  • Sul'Gin Sergej Mikhajlovich
  • Fin'Ko Oleg Anatol'Evich
  • Shcherbakov Andrej Viktorovich
  • Samojlenko Dmitrij Vladimirovich
  • Sharaj Vjacheslav Aleksandrovich
RU2417405C2
MODULE FOR BOOLEAN FUNCTION LOGIC TRANSFORMATION 0
  • Yanushkevich Svetlana Nikolaevna
  • Morozova Anna Anatolevna
  • Kukharev Georgij Aleksandrovich
  • Shmerko Vladimir Petrovich
SU1667050A1
SELF-CHECKING SPECIAL-PURPOSE COMPUTER OF BOOLEAN FUNCTION SYSTEMS 2012
  • Dichenko Sergej Aleksandrovich
  • Vishnevskij Artem Konstantinovich
  • Fin'Ko Oleg Anatol'Evich
RU2485575C1
METHOD FOR NOISELESS GRADIENT SELECTION OF OBJECT CONTOURS ON DIGITAL IMAGES 2015
  • Pantyukhin Maksim Aleksandrovich
  • Samojlin Evgenij Aleksandrovich
RU2589301C1
METHOD AND ARRANGEMENT FOR LOCAL RULE OF TRAINING COMPETITION, WHICH LEADS TO A SPARSE CONNECTIVITY 2012
  • Aparin Vladimir
RU2586864C2

RU 2 402 813 C1

Authors

Samojlin Evgenij Aleksandrovich

Dates

2010-10-27Published

2009-06-18Filed