# diego-vicente/som-tsp

Solving the Traveling Salesman Problem using Self-Organizing Maps

Repository: https://github.com/diego-vicente/som-tsp
Canonical: https://ross.abutalabs.com/products/som-tsp
Homepage: https://diego.codes/post/som-tsp/
Language: Python
License: MIT
License Family: permissive
Topics: self-organizing-map, som, tsp, tsp-problem, tsp-approximation, traveling-salesman
Last push: 2023-12-24T16:40:59+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3222, "days_push": 983, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_readme
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3933, forks 599 (observed 2026-08-28T04:08:30.035350+00:00)

## What it is
A Python implementation that solves the Traveling Salesman Problem using Self-Organizing Maps, a neural network technique adapted to find approximate TSP routes. It provides an approximation algorithm for this NP-complete problem rather than an exact solution.

## Use cases
- solve the traveling salesman problem with a self-organizing map
- find approximate TSP routes for city datasets
- learn how SOMs can be applied to combinatorial optimization
- compare TSP approximation heuristics
- visualize how a SOM converges on a route
- benchmark sub-optimal TSP solvers in Python

## When to choose
- you need a quick approximate solution to a TSP instance
- you want a readable educational implementation of SOM-based TSP solving
- you are researching neural approaches to combinatorial optimization

## When to avoid
- you need a provably optimal TSP solution
- you require high-performance solving of very large instances
- you need a maintained production library with active development

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, simulation, math
- domain: artificial-intelligence, data-science
- platform: python, cross-platform
- tags: self-organizing-map, traveling-salesman-problem, tsp-approximation, neural-network, optimization, algorithms

## Member repositories
- diego-vicente/som-tsp (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:30.035350+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:24:40.047681+00:00, confidence not recorded.
  - homepage: https://diego.codes/post/som-tsp/ (fetched 2026-08-29T09:18:30.960386+00:00, sha b37656e69082)
  - site_page: https://diego.codes/about (fetched 2026-08-29T09:18:30.969767+00:00, sha a243b31f478b)
- Data as of 2026-08-30T08:39:29.467469+00:00.