On Correspondences between Feedforward Artificial Neural Networks on Finite Memory Automata and Classes of Primitive Recursive Functions

On Correspondences between Feedforward Artificial Neural Networks on Finite Memory Automata and Classes of Primitive Recursive Functions

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...

Full description

Bibliographic Details
Main Author: Vladimir A. Kulyukin
Format: Article
Language:English
Published: MDPI AG 2023-06-01
Series:Mathematics
Subjects:
computability theory
theory of recursive functions
artificial neural networks
number theory
Online Access:https://www.mdpi.com/2227-7390/11/12/2620

Internet

https://www.mdpi.com/2227-7390/11/12/2620

Similar Items