JustGlowing/minisom

Health v2 · maintenance only

Adoption not part of the score

1601 stars · 444 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

MiniSom is a minimalistic, NumPy-based Python implementation of Self Organizing Maps (SOM), a type of neural network for unsupervised learning, with optional Numba JIT acceleration. It is designed to be simple and readable so researchers can extend it and students can quickly understand the algorithm.

Use cases

• cluster high-dimensional data with a self-organizing map
• reduce dimensionality of my dataset for visualization
• perform vector quantization on numpy data
• detect outliers in unlabeled data
• learn how SOMs work by reading a simple implementation
• visualize nonlinear relationships in high-dimensional data on a 2D map

When to choose

• you need a lightweight, dependency-minimal SOM implementation in Python
• you want readable source code to study or extend the SOM algorithm
• you work with NumPy arrays and want easy integration into a scientific Python stack
• you want optional JIT speedups via Numba

When to avoid

• you need a full deep learning framework with GPU training and rich model tooling
• you need supervised learning or other neural network architectures
• you need highly optimized, distributed training for very large datasets

Facets

library · maturity stable

machine-learning data-science machine-learning data-science python self-organizing-map som unsupervised-learning clustering dimensionality-reduction vector-quantization numpy numba

Member repositories

For agents

markdown · JSON · MCP: product_card(name="JustGlowing/minisom")