An inertial neuro-dynamic system for solving zero-one integer programming

This paper presents an inertial neuro-dynamic system to solve zero-one integer programming. We transform the problem of zero-one integer programming into a relatively easy problem only subject to linear equality constraints by using a nonlinear complementarity problem function. Subsequently, a inert...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2021 International Conference on Neuromorphic Computing (ICNC) S. 314 - 319
Hauptverfasser: Wei, Shuting, He, Xing
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 15.10.2021
Schlagworte:
Convergence
inertial factor
inertial neuro-dynamic system
Integer programming
Neuromorphic engineering
Reliability
Transforms
zero-one integer programming
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:This paper presents an inertial neuro-dynamic system to solve zero-one integer programming. We transform the problem of zero-one integer programming into a relatively easy problem only subject to linear equality constraints by using a nonlinear complementarity problem function. Subsequently, a inertial neuro-dynamic system is proposed to solve above transformed problem. It is shown that the proposed inertial neuro-dynamic system is stable and the equilibrium point converges to optimal solution set. It is worth emphasizing that our developed inertial neuro-dynamic system achieves faster convergence speed and explores more optimal solutions in a fixed initial value by adjusting the inertial factor. Finally, according to the experimental results on two illustrative examples, the proposed method is highly effective.
DOI:10.1109/ICNC52316.2021.9608378