FIELD: computer technology.
SUBSTANCE: invention relates to smart controllers using a genetic algorithm for search for a neural network structure and weight coefficients of its synoptical connections. A device contains an object of control, a block for training a neural network, a block for assessment of neural network performance, a data block, a neural network block, a block of a random number generator, a control block, a hybridization block, a mutation block, a chromosome history block, a chromosome selection block.
EFFECT: increase in the speed of finding a suboptimal neural network satisfying set indicators of the quality of operation.
1 cl, 1 dwg
| Title | Year | Author | Number |
|---|---|---|---|
| NEURAL NETWORK TRAINING CONTROLLER WITH GENETIC ALGORITHM | 2015 |
|
RU2602973C1 |
| MODIFIED INTELLIGENT CONTROLLER WITH ADAPTIVE CRITIC | 2024 |
|
RU2836598C1 |
| INTELLIGENT CONTROLLER WITH SELF-MODIFICATION RULES OF EDUCATIONAL AND CONTROL NEURAL NETWORKS | 2011 |
|
RU2447494C1 |
| DEVICE FOR HARDWARE IMPLEMENTATION OF EVOLUTIONARY ALGORITHM WITH INEXPLICIT OPERATORS | 2010 |
|
RU2447503C1 |
| MODIFIED INTELLIGENT CONTROLLER WITH FUZZY RULES AND NEURAL NETWORK TRAINING UNIT | 2021 |
|
RU2774625C1 |
| METHOD AND DEVICE FOR OPTIMIZING PARAMETERS OF STRATEGY FOR LONG-TERM PLANNING OF MEASURES TO ENSURE REQUIRED STATE OF COMPLEX ORGANIZATIONAL AND TECHNICAL SYSTEM | 2019 |
|
RU2706458C1 |
| RECONFIGURABLE DEVICE FOR HARDWARE IMPLEMENTATION OF GENETIC ALGORITHM | 2014 |
|
RU2572379C1 |
| SPLICING SITES CLASSIFICATION BASED ON DEEP LEARNING | 2018 |
|
RU2780442C2 |
| AUTOMATIC SYSTEM FOR CONTROLLING MOVEMENT OF MOBILE OBJECT AND METHOD FOR AUTOMATIC CONTROL OF MOVEMENT OF MOBILE OBJECT | 2009 |
|
RU2451593C2 |
| DEVICE FOR HARDWARE REALIZATION OF PROBABILITY GENETIC ALGORITHMS | 2005 |
|
RU2294561C2 |
