On the possibility of implementing artificial intelligence systems based on error-correcting code algorithms


Bakirov A.S. Suleimenov I.E.
15 January 2021Little Lion Scientific

Journal of Theoretical and Applied Information Technology
2021#99Issue 183 - 99 pp.

A new approach to the implementation of artificial intelligence systems is proposed, based on an analogy with the theory of error-correcting coding, as well as on the philosophical interpretation of intelligence as an information processing system that provides, first of all, its compression, for example, by reducing some complex digital image to a set of classification features. The approach is based on the expansion of the binary sequence into a fuzzy Fourier series, implying that the expansion approximates the original function up to a certain number of permissible deviations. This solves a problem similar to that which artificial neural networks solve, leading the recognizable image to the image from the original training set. The analogs of the images that make up the training sample are functions that form the basis for the expansion of the binary sequence into a fuzzy Fourier series and/or their combination.

Artificial intelligence , Artificial neural networks , Dialectical positivism , Error-correcting codes

Text of the article Перейти на текст статьи

Almaty University of Power Engineering and Telecommunications, Almaty, Kazakhstan
National Academy of Engineering of the Republic of Kazakhstan, Almaty, Kazakhstan

Almaty University of Power Engineering and Telecommunications
National Academy of Engineering of the Republic of Kazakhstan

10 лет помогаем публиковать статьи Международный издатель

Книга Публикация научной статьи Волощук 2026 Book Publication of a scientific article 2026