FIELD: computer engineering.
SUBSTANCE: invention relates to computer engineering and can be used in digital computing devices, as well as in end fields GF(2ν) elements formation devices. Technical result is achieved by using new activation function in hidden layer, use of synaptic weights ωi,j, equal to one, which enables to eliminate synaptic weights multipliers from formal neuron structure, as well as elimination from neuron structure of output layer of unit,implementing activation function calculations.
EFFECT: technical result consists in reduction of system expenses required for multi-input adder realization by module two.
1 cl, 1 dwg
| Title | Year | Author | Number |
|---|---|---|---|
| DEVICE FOR DETERMINATION OF NUMBER OF UNITS IN BINARY EIGHT-DIGIT CODE | 1991 |
|
RU2030783C1 |
| MODULO MULTIPLIER | 2015 |
|
RU2589361C1 |
| DEVICE FOR CALCULATING FACTOR OF GENERALISED POLYADIC ERROR CORRECTION | 2015 |
|
RU2584495C1 |
| 0 |
|
SU1783627A1 | |
| METHOD AND DEVICE FOR AUTOMATIC RECOGNITION OF RADIO SIGNALS MANIPULATION TYPE | 2016 |
|
RU2619717C1 |
| DIGITAL FILTERING DEVICE | 0 |
|
SU1348815A1 |
| SYSTEM FOR OPERATIONAL IDENTIFICATION OF MARINE TARGETS BY THEIR INFORMATION FIELDS BASED ON NEURO-FUZZY MODELS | 2021 |
|
RU2763384C1 |
| METHOD AND DEVICE FOR AUTOMATIC RECOGNITION OF RADIO SIGNAL MANIPULATION TYPE | 2017 |
|
RU2665235C1 |
| NEURAL NETWORK-BASED NEURAL NETWORK CONSTRUCTION WITH FUNCTIONAL TRANSFORMATION OF ARBITRARY TYPE FOR INPUT SIGNALS | 2018 |
|
RU2727080C2 |
| SYSTEM FOR DETECTING AND CLASSIFYING NAVAL TARGETS BASED ON NEURAL NETWORK TECHNOLOGIES AND ARTIFICIAL INTELLIGENCE ELEMENTS | 2021 |
|
RU2780607C1 |
