Cognitive Architecture for Decision-Making Based on Brain Principles Programming (in Russian)
This work proposes a novel cognitive architecture for AI decision-making, but it appears incremental as it builds on existing brain-inspired principles without demonstrating clear performance gains.
The authors developed a cognitive architecture based on five brain activity principles to solve diverse problems, implementing it through three subsystems: logical-probabilistic inference, probabilistic formal concepts, and functional systems theory, with examples provided for practical applications.
We describe a cognitive architecture intended to solve a wide range of problems based on the five identified principles of brain activity, with their implementation in three subsystems: logical-probabilistic inference, probabilistic formal concepts, and functional systems theory. Building an architecture involves the implementation of a task-driven approach that allows defining the target functions of applied applications as tasks formulated in terms of the operating environment corresponding to the task, expressed in the applied ontology. We provide a basic ontology for a number of practical applications as well as for the subject domain ontologies based upon it, describe the proposed architecture, and give possible examples of the execution of these applications in this architecture.