Architecture of multi-agent neurocognitive system providing semantic representation of multimodal images in technology of machine vision

I.A. Pshenokova, O.V. Nagoeva, Z.A. Sundukov, V.A. Denisenko

Institute of Computer Science and Problems of Regional Management – branch of Federal public budgetary scientific establishment “Federal scientific center “Kabardin-Balkar Scientific Center of the RussianAcademy of Sciences”

Annotation: This article represents a method for formalizing the semantics of natural language patterns based on the self-organization of multi-agent neurocognitive architectures. An architecture has been developed for creating conceptual agents that provide a semantic representation of images in a computer vision system.

The algorithm of image recognition and natural language understanding using multimodal interface is demonstrated.

Keywords: multi-agent system, natural language interface, image recognition, formal semantics, natural language understanding, intelligence system, neurocognitive architecture.