Document Type
Article
Author ORCID Identifier
Vladimir A. Kulyukin https://orcid.org/0000-0002-8778-5175
Journal/Book Title/Conference
Mathematics
Volume
11
Issue
12
Publisher
MDPI AG
Publication Date
6-8-2023
First Page
1
Last Page
25
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Abstract
When realized on computational devices with finite quantities of memory, feedforward artificial neural networks and the functions they compute cease being abstract mathematical objects and turn into executable programs generating concrete computations. To differentiate between feedforward artificial neural networks and their functions as abstract mathematical objects and the realizations of these networks and functions on finite memory devices, we introduce the categories of general and actual computabilities and show that there exist correspondences, i.e., bijections, between functions computable by trained feedforward artificial neural networks on finite memory automata and classes of primitive recursive functions.
Recommended Citation
Kulyukin, V.A. On Correspondences between Feedforward Artificial Neural Networks on Finite Memory Automata and Classes of Primitive Recursive Functions. Mathematics 2023, 11, 2620. https://doi.org/10.3390/math11122620
