UDC 004.415.2

Authors

Averkin A.N.
Federal Research Center "Informatics and Management" of the Russian Academy of Sciences; Plekhanov Russian University of Economics, Moscow, Russia
Yarushev S.A.
Plekhanov Russian University of Economics, Moscow, Russia
Savinova V.M.
Plekhanov Russian University of Economics, Moscow, Russia

Abstract

The successes achieved in the development of artificial intelligence systems give rise to a number of new tasks, in particular, the tasks of understanding and recognizing a natural language. Work on these tasks can significantly improve semantic systems, information retrieval tasks, pattern discovery, event and anomaly recognition, knowledge base creation and much more. These technologies are successfully implemented in security services, in voice assistants, such as Alice from Yandex or Siri from Apple. Now a new class of problems arises, the ability of systems to understand the language and be able to give conclusions based on recognized images. In this paper, we set the task of automated analytics based on the hybridization of image recognition systems and semantic analysis.

Keywords

Artificial intelligence, Deep neural network, Hybrid deep network, Capsule network, Decision support