Result: Polynomial-Computable Representation of Neural Networks in Semantic Programming

Title:
Polynomial-Computable Representation of Neural Networks in Semantic Programming
Authors:
Sergey Goncharov, Andrey Nechesov
Source:
J, Vol 6, Iss 1, Pp 48-57 (2023)
Volume 6
Issue 1
Pages: 48-57
Publisher Information:
MDPI AG, 2023.
Publication Year:
2023
Subject Terms:
polynomiality, machine learning, semantic programming, AI, Science, logical programming language, polynomial algorithm, neural networks
Document Type:
Academic journal Article<br />Other literature type
File Description:
application/pdf
Language:
English
ISSN:
2571-8800
DOI:
10.3390/j6010004
Access URL:
https://doaj.org/article/a1a34c2bf92f4ef9b4d228bc0af62f25
Rights:
CC BY
Accession Number:
edsair.doi.dedup.....9653f45b8f51e91118325c1bcc7d047e
Database:
OpenAIRE

Further Information

A lot of libraries for neural networks are written for Turing-complete programming languages such as Python, C++, PHP, and Java. However, at the moment, there are no suitable libraries implemented for a p-complete logical programming language L. This paper investigates the issues of polynomial-computable representation neural networks for this language, where the basic elements are hereditarily finite list elements, and programs are defined using special terms and formulas of mathematical logic. Such a representation has been shown to exist for multilayer feedforward fully connected neural networks with sigmoidal activation functions. To prove this fact, special p-iterative terms are constructed that simulate the operation of a neural network. This result plays an important role in the application of the p-complete logical programming language L to artificial intelligence algorithms.