On the Possibility to Resolve the Scientific Paradoxes in Artificial Cognitive System
LPI, Moscow, Leninskii av. 531 pp. (accepted)
The concept of scientific paradox and the possibility to reveal and resolve these paradoxes by means of artificial intelligence are discussed. The cognitive architecture designed under the Natural-Constructive Approach for modeling the cognitive process is presented. This approach is aimed to interpret and reproduce the human-like cognitive features including uncertainty, individuality, intuitive and logical thinking, and the role of emotions in cognitive process. It is shown that this architecture involves, in particular, the high-level symbolic information that could be associated with concept of “science”. The scientific paradox is treated as impossibility to merge different representations of the same object. It is shown that these paradoxes could be resolved within the proposed architecture by decomposition of the high-level symbols into low-level of corresponding “images”, with subsequent revision of the object’s memorization procedure.