FIELD: information technology.
SUBSTANCE: invention relates to oscillatory neural networks of pulse type and can be used for identification and classification of images. Method is a procedure for calculating a family of metrics, consisting of two parameters – high-order synchronization ratio (SHR) and synchronization efficiency value (η). At that, synchronization (of one or group of oscillators) is calculated relative to the master oscillator having constant oscillation frequency.
EFFECT: providing memorization and recognition of multiple images using one input layer of the network.
1 cl, 6 dwg
| Title | Year | Author | Number |
|---|---|---|---|
| METHOD OF PATTERN RECOGNITION IN A SYSTEM OF COUPLED OSCILLATORS | 2018 |
|
RU2697947C1 |
| INTERACTION METHOD IN THE OXIDE STRUCTURES WITH THE ELECTRICAL SWITCHING EFFECT BASED COUPLED OSCILLATORS SYSTEM | 2017 |
|
RU2663546C1 |
| METHOD OF FORMING TWO-DIMENSIONAL IMAGE OF BIOSIGNAL AND ANALYSIS THEREOF | 2013 |
|
RU2538938C2 |
| METHOD OF DETECTING AND CLASSIFYING SEA TARGETS USING A MATHEMATICAL MODEL OF DETERMINING THE TYPE OF TARGET | 2020 |
|
RU2724990C1 |
| SYSTEM FOR OPERATIONAL IDENTIFICATION OF MARINE TARGETS BY THEIR INFORMATION FIELDS BASED ON NEURO-FUZZY MODELS | 2021 |
|
RU2763384C1 |
| METHOD FOR OPERATIONAL IDENTIFICATION OF MARINE TARGETS BY THEIR INFORMATION FIELDS BASED ON NEURO-FUZZY MODELS | 2021 |
|
RU2763125C1 |
| SYSTEM FOR DETECTING AND CLASSIFYING NAVAL TARGETS BASED ON NEURAL NETWORK TECHNOLOGIES AND ARTIFICIAL INTELLIGENCE ELEMENTS | 2021 |
|
RU2780607C1 |
| METHOD FOR DETECTING AND CLASSIFYING NAVAL TARGETS BASED ON NEURAL NETWORK TECHNOLOGIES AND ARTIFICIAL INTELLIGENCE ELEMENTS | 2021 |
|
RU2780606C1 |
| METHOD FOR DETERMINING STRUCTURE AND DEMODULATION OF SIGNAL WITH UNKNOWN STRUCTURE | 2008 |
|
RU2386165C2 |
| METHOD FOR AMALYZING MEDICAL DATA USING NEURAL NET LogNNet | 2021 |
|
RU2754723C1 |
