A variety of globally stable periodic orbits in permutation binary neural networks

DOI10.3934/DCDSB.2023078zbMATH Open1521.37023arXiv2301.02801OpenAlexW4367164204MaRDI QIDQ6156579FDOQ6156579

Mikito Onuki, T. Saito, Kento Saka

Publication date: 13 June 2023

Published in: Discrete and Continuous Dynamical Systems. Series B (Search for Journal in Brave)

Abstract: The permutation binary neural networks are characterized by global permutation connections and local binary connections. Although the parameter space is not large, the networks exhibit various binary periodic orbits. Since analysis of all the periodic orbits is not easy, we focus on globally stable binary periodic orbits such that almost all initial points fall into the orbits. For efficient analysis, we define the standard permutation connection that represents multiple equivalent permutation connections. Applying the brute force attack to 7-dimensional networks, we present the main result: a list of standard permutation connections for all the globally stable periodic orbits. These results will be developed into detailed analysis of the networks and its engineering applications.

Full work available at URL: https://arxiv.org/abs/2301.02801

Recommendations

• Permutation binary neural networks: analysis of periodic orbits and its applications
• scientific article; zbMATH DE number 1833335
• Stable periodic orbits in nonlinear discrete-time neural networks with delayed feedback
• scientific article; zbMATH DE number 852160
• The stable periodic solutions of a discrete neural network system
• Periodic oscillation for a class of neural networks with variable coefficients
• Global exponential periodicity and global exponential stability of a class of recurrent neural networks
• Advances in Neural Networks – ISNN 2005
• Periodicity and stability issues of a chaotic pattern recognition neural network

zbMATH Keywords

permutationstabilityrecurrent neural networksbinary neural networksbinary periodic orbits

Mathematics Subject Classification ID

Periodic orbits of vector fields and flows (37C27) Stability theory for smooth dynamical systems (37C75)

Cites Work

• Neural networks and physical systems with emergent collective computational abilities.
• Chaos in Dynamical Systems
• ``Neural computation of decisions in optimization problems
• Design of CAECC - cellular automata based error correcting code
• Associative dynamics in a chaotic neural network.
• A simple digital spiking neural network: synchronization and spike-train approximation
• Completely reproducible description of digital sound data with cellular automata
• Permutation binary neural networks: analysis of periodic orbits and its applications

This page was built for publication: A variety of globally stable periodic orbits in permutation binary neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6156579)