STRUCTURAL SYNTHESIS OF HYBRID NEURAL NETWORKS ENSEMBLES
Journal Title: Електроніка та системи управління - Year 2018, Vol 3, Issue 57
Abstract
It is considered the structural synthesis of hybrid neural networks ensembles. It is chosen the ensemble topology as parallel structure with united layer. It is developed a hybrid algorithm for the problem solution which includes some algorithms preliminary choice of classifiers(modules of neural networks-hybrid neural networks, which consist of Kohonen, basic neural networks and bi-directional associative memory), creation the bootstrap training samples for every classifier, training these classifiers, optimal choice of necessity ones, determination of layer union weight coefficients, ensemble pruning. For the solution of optimal choice classifiers it is used two criteria: accuracy and variety.
Authors and Affiliations
Victor Sineglazov, Olena Chumachenko, Oleksiy Bedukha
Keywords
Related Articles
- EP ID EP517271
- DOI 10.18372/1990-5548.57.13242
- Views 136
- Downloads 0
ALGORITHM OF OPTIMAL CONTROL OF UAV GROUP
The article proposes the algorithm of optimal control of unmanned aerial vehicle group allowing to set maneuvers of unmanned aerial vehicles, to estimate the coordinates of current position of unmanned aerial vehicle rel...
DIAGNOSTIC SYSTEM BASED ON AUTOENCODERS
It`s considered the problem of image processing which is used in diagnostic systems when it is necessary to process the results of ultrasound, computed tomography and magnetic resonance imaging. For the solution of this...
FUZZY AUTOMATIC CONTROL SYSTEM SYNTHESIS OF THE PROPELLER FAN THE AVIATION GAS TURBINE ENGINE
The article deals with the method of automatic control systems synthesis of with a fuzzy controller, which is considered as a separate subsystem within the general control system. Due to the use of the harmonic lineariza...
ACHIEVEMENTS IN THE FIELD OF CREATION SOLAR POWER STATION
An overview of publications in the field of creating power plants using solar radiation energy - solar stations is given. It is shown that solar energy is the source of energy of the future, an exceptionally clean, simpl...
ALGORITHM OF PRUNING OF HYBRID NEURAL NETWORKS ENSEMBLE
Despite the fact that the ensemble is usually more accurate than a single network, existing ensemble techniques tend to create unreasonably large ensembles that increase the use of memory and computation costs. The ensem...