FIELD: computer systems.
SUBSTANCE: invention can be used for constructing neural networks for temporal or spatial prediction of parameters of studied objects or pattern recognition. Computer system is realized based on neural network, which includes at least one neuron, using functional transformation of arbitrary type, specified in the form of a table (array) of matching pairs of input data and an output function for each input signal with subsequent summation, wherein values of tabular transformation functions are selected stochastically based on a genetic algorithm when training a neural network.
EFFECT: technical result is higher degree of freedom of individual neurons and thereby reduced depth of network.
1 cl, 5 dwg
| Title | Year | Author | Number |
|---|---|---|---|
| NEURON SIMULATION METHOD | 2009 |
|
RU2402813C1 |
| ARTIFICIAL NEURAL NETWORK | 2014 |
|
RU2573766C1 |
| ANALOGUE HARDWARE IMPLEMENTATION OF NEURAL NETWORKS | 2020 |
|
RU2796649C2 |
| METHOD FOR DETERMINING THE OPTICAL POWER OF AN INTRAOCULAR LENS USING AN ARTIFICIAL NEURAL NETWORK | 2022 |
|
RU2791204C1 |
| METHOD OF TRAINING ARTIFICIAL NEURAL NETWORK | 2014 |
|
RU2566979C1 |
| METHOD TO CONTROL COMPUTER NETWORK | 2014 |
|
RU2542901C1 |
| EXPRESS-METHOD FOR PREDICTING FIRE-HAZARDOUS PROPERTIES OF LIMITING ALDEHYDES WITH USE OF MOLECULAR DESCRIPTORS AND ARTIFICIAL NEURAL NETWORKS | 2018 |
|
RU2672268C1 |
| METHOD OF TRAINING ARTIFICIAL NEURAL NETWORK | 2012 |
|
RU2504006C1 |
| ARTIFICIAL NEURAL NETWORK TRAINING METHOD | 2019 |
|
RU2723270C1 |
| METHOD OF TRAINING DEEP NEURAL NETWORKS BASED ON DISTRIBUTIONS OF PAIRWISE SIMILARITY MEASURES | 2016 |
|
RU2641447C1 |
