Open AccessNeuroevolutionary reinforcing learning of neural networks
Author(s) -
Y. A. Bury,
Debashisa Samal
Publication year - 2022
Publication title -
sistemnyj analiz i prikladnaâ informatika
Language(s) - English
Resource type - Journals
eISSN - 2414-0481
pISSN - 2309-4923
DOI - 10.21122/2309-4923-2021-4-16-24
Subject(s) - artificial neural network , computer science , network topology , artificial intelligence , process (computing) , dimension (graph theory) , evolutionary acquisition of neural topologies , nervous system network models , types of artificial neural networks , deep learning , recurrent neural network , machine learning , time delay neural network , mathematics , pure mathematics , operating system
The article presents the results of combining 4 different types of neural network learning: evolutionary, reinforcing, deep and extrapolating. The last two are used as the primary method for reducing the dimension of the input signal of the system and simplifying the process of its training in terms of computational complexity. In the presented work, the neural network structure of the control device of the modeled system is formed in the course of the evolutionary process, taking into account the currently known structural and developmental features of self-learning systems that take place in living nature. This method of constructing it makes it possible to bypass the specific limitations of models created on the basis of recombination of already known topologies of neural networks.