Artificial Intelligence and Number System in Residual Classes

• Published in: 2021 IEEE 4th International Conference on Advanced Information and Communication Technologies (AICT) pp. 171 - 176
• Main Authors: Krasnobayev, Victor, Kuznetsov, Alexandr, Bagmut, Mykhaylo, Kuznetsova, Tetiana
• Format: Conference Proceeding
• Language: English
• Published: IEEE 21-09-2021
• Subjects: Artificial Intelligence; Biological system modeling; Brain modeling; Buildings; Human intelligence; Information processing; Information Processing by the Human Brain; Non-Positional Number System; Number System in Residual Classes; Redundancy; Search problems
• DOI: 10.1109/AICT52120.2021.9628970

This article discusses a model of the process of information processing by the human brain, based on the assumption that the storage and processing of information is carried out in a non-positional number system in residual classes (RNS). When accepting the hypothesis about the holographic principle of information processing by the human brain, the expediency and effectiveness of building artificial intelligence systems based on the information processing model in the RNS is obvious. This is due to the fact that the principles and methods of information processing in the RNS are in good agreement with modern concepts and ideas about the process of information processing by the human brain. The accuracy of the description (representation) of the information object G depends on the number and values of the RNS bases. So, the larger the number of RNS bases and the larger they are in value, the more accurately the information object G is described by means of frames. This fact confirms the expediency of using the RNS.