ATTENTION/WARNING - NE PAS DÉPOSER ICI/DO NOT SUBMIT HERE

Ceci est la version de TEST de DIAL.mem. Veuillez ne pas soumettre votre mémoire sur ce site mais bien à l'URL suivante: 'https://thesis.dial.uclouvain.be'.
This is the TEST version of DIAL.mem. Please use the following URL to submit your master thesis: 'https://thesis.dial.uclouvain.be'.
 

Solving the traveling salesman problem using deep learning: a ground-up approach

Nepper, Nathan
(2023)

Files

Nepper_14281800_2023.pdf
  • UCLouvain restricted access
  • Adobe PDF
  • 5.15 MB

Details

Supervisors
Schaus, Pierre ; Coppé, Vianney ; Burlats, Auguste
Faculty
Ecole polytechnique de Louvain
Degree label
Master [120] en sciences informatiques, à finalité spécialisée
Abstract
This thesis explores the application of Deep Learning to the Traveling Salesman Problem (TSP) within Combinatorial Optimization. We highlighted the limitations of Feed-Forward neural networks, leading to the adoption of the Sequence-to-Sequence and Pointer Network frameworks. The Transformer Architecture was validated for TSP, aligning with the Geometric Deep Learning approach. Our experiments, based on Kool et al. (2019)'s architecture, confirmed several literature findings.