A gentle introduction to deep neural networks for operations researchers

• Pau Amaré ^[1] ; Jordi Castro ^[1]
  1. [1] Universitat Politècnica de Catalunya

     Universitat Politècnica de Catalunya

     Barcelona, España

     
• Localización: Sort: Statistics and Operations Research Transactions, ISSN 1696-2281, Vol. 50, Nº. 1, 2026, págs. 89-116
• Idioma: inglés
• DOI: 10.57645/20.8080.02.33
• Enlaces
  • Texto completo (pdf)
• Resumen

  • Computing a neural network is, in essence, a large unconstrained optimization problem, though this fact is often obscured by machine learning jargon. We present a gentle introduction to deep learning for operations researchers, describing in a didactic manner the underlying optimization problem and providing examples developed from scratch. These examples are solved using both standard modeling languages and modern machine learning frameworks. We conclude by discussing applications of neural networks in operations research, illustrated through a concrete example involving the knapsack problem.