Denisenko V. A., Nagoev Z. V., Nagoeva O. V. Computer system design based on the recursive cognitive architecture for synthesis of an intelligent agent behavior

Abstract: The authors suggested an approach to solving a fundamental problem of artificial intelligence (AI) of formalization of the semantics of rational thinking with the use of cognitive modeling based on the concept of recursive (fractal) cognitive architecture and a hypothesis of invariant of organizational and functional structure of the process of intelligent decision based on the cognitive functions. This researches with previously suggested method of learning in a multiagent neural like systems based on the ontoneuromorphogenesis are leading to the creation of self-organizing multiagent emergent networks, capable of simulation of psyche functions, goal-setting and adaptive goal-directed behavior based on the semantization of reality and building social connections. The principles of cognitive organization of intelligent systems are tightly connected with multiagent division of functions in multicellular organisms. Cognitive centers as in human brain as well as in an artificial intelligent system should be made as active systems, interworking with each other on the basis of the collective optimization parameters, critical in the first place to maintain the integrity of the system and its survival. Formal description of the agent should take into account that agent’s behavior consists of actions, which are carried out in the agent’s habitat and require energy. It is also important to note, that the exchange of energy and information happens not only between agent and the environment, but also between inside agents (organs, neurons) of the agent of a top level of recursive cognitive architecture.

Keywords: