Optimization of Sparsity-Constrained Neural Networks as a Mixed Integer Linear Program

The literature has shown how to optimize and analyze the parameters of different types of neural networks using mixed integer linear programs (MILP). Building on these developments, this work presents an approach to do so for a McCulloch/Pitts and Rosenblatt neurons. As the original formulation invo...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Journal of optimization theory and applications 2023-12, Vol.199 (3), p.931-954
1. Verfasser:	Rosenhahn, Bodo
Format:	Artikel
Sprache:	eng
Schlagworte:	Constraints Integer programming Linear programming Mixed integer Neural networks Neurons Optimization Parameters Sparsity
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!