FIELD: processing of data for special uses, in particular, for transforming images, set by non-weighted digital codes, to weighted codes.
SUBSTANCE: in accordance to the invention the device contains a group of parallel adders, a group of blocks for multiplication by weight coefficients, a group of parallel multipliers, a block for forming image fragments and a group of threshold blocks, group of blocks for binary disjunction of vectors and block for generation of a random binary low density vector.
EFFECT: expanded functional capabilities and increased trustworthiness of image recognition.
2 dwg
| Title | Year | Author | Number |
|---|---|---|---|
| SINGLE-LAYER PERCEPTRON BASED ON SELECTIVE NEURONS | 2015 |
|
RU2597497C2 |
| NEURON SIMULATION OF REAL NEURON PROPERTIES | 2014 |
|
RU2597495C2 |
| INSTRUMENTAL METHOD OF TRAINING SELECTIVE NEURAL NETWORK WITHOUT MATHEMATICS AND WITHOUT A TEACHER WITH USE OF SELF-ORGANIZATION | 2019 |
|
RU2729878C2 |
| NEAR-REAL IMPULSE NEURON | 2015 |
|
RU2598298C2 |
| NEURON SIMULATION METHOD | 2009 |
|
RU2402813C1 |
| DEVICE FOR SIMULATING NEURON NETWORKS | 1990 |
|
RU2045778C1 |
| SINGLE-LAYER PERCEPTRON, SIMULATING REAL PERCEPTRON PROPERTIES | 2015 |
|
RU2597496C1 |
| METHOD AND DEVICE FOR AUTOMATIC RECOGNITION OF RADIO SIGNALS MANIPULATION TYPE | 2016 |
|
RU2619717C1 |
| DEVICE FOR COLOURING BLACK AND WHITE IMAGE | 2013 |
|
RU2524869C1 |
| METHOD AND DEVICE FOR AUTOMATIC RECOGNITION OF RADIO SIGNAL MANIPULATION TYPE | 2017 |
|
RU2665235C1 |
