|Title of the article||
METHODS OF NEURAL NETWORKS AND DEEP LEARNING ON THE BASIS OF AN INTELLIGENT AGENT
Amandos D. Tulegulov, Candidate of physical and mathematical sciences, associate professor, head of sub-department of aviation engineering and technology, Academy of Civil Aviation (44 Akhmetova street, Almaty, Kazakhstan), E-mail: firstname.lastname@example.org
Background. New tasks arising almost daily lead to the emergence of new directions of machine learning. The article presents the results of the study of the main types of machine learning on the basis of the availability and complexity of data. Materials and methods. The main research method is the selection method. For each specific task, its algorithm is selected, since the speed and accuracy of the result of processing the source data depends on it. We consider methods of machine learning. In particular, an option is analyzed based on the training of an intelligent agent, which acts in the external environment and is called training with reinforcement. Reinforcement training (Eng. Reinforcement Learning) is a method of machine learning, in which the system is learning, interacting with some medium. Results. As a result of research, it is possible to note the fact that in training with reinforcement an agent interacts with the environment, taking actions and receives a reward for these actions. Conclusions. In this way, it can be argued that at the moment the classic methods of machine learning for digital technologies cover a wide range of applications from different consumers. New tasks arising almost daily lead to the emergence of new directions of machine learning.
algorithm, artificial intelligence, machine learning, data mining, methods
Дата обновления: 18.11.2021 09:26