Solving the Traveling Salesman Problem using Self-Organizing Maps

:red_circle: MiniSom is a minimalistic implementation of the Self Organizing Maps

Python implementation of the Epigenetic Robotic Architecture (ERA). It includes standalone classes for Self-Organizing Maps (SOM) and Hebbian Networks.

Recursive Self-Organizing Map/Neural Gas.

Self organizing Kohonen map in Python with periodic boundary conditions

Implementation of SOM and GSOM

Using Self-Organizing Maps for Travelling Salesman Problem

Growing Hierarchical Self-Organizing Map (GHSOM) implementation in C++

Efficient Self-Organizing Map for Sparse Data

SUSI: Python package for unsupervised, supervised and semi-supervised self-organizing maps (SOM)

Pytorch implementation of Self-Organizing Map(SOM). Use MNIST dataset as a demo.

A basic implementation of a Kohonen map in JavaScript

Deep Embedded Self-Organizing Map: Joint Representation Learning and Self-Organization

SOM clustering on IRIS dataset

TRIQS-based Stochastic Optimization Method for Analytic Continuation

Parallelized rotation and flipping INvariant Kohonen maps

Rust library for Self Organising Maps (SOM).

Huge-scale, high-performance flow cytometry clustering in Julia

A custom C API for instrumenting Jetson TX1’s SoM and SoC

Exercicios para practicar comandos en bash

Neural network with learning without a teacher, performing the task of visualization and clustering.

Experimental implementation of Self-Organizing Map

Pytorch extension implementing LISSOM network and Topographica features

SOMperf: Self-organizing maps performance metrics and quality indices

A python machine learning library, with powerful customization for advanced users, and robust default options for quick implementation.

Spark ML implementation of SOM algorithm (Kohonen self-organizing map)

Self Organizing Map (SOM) is a type of Artificial Neural Network (ANN) that is trained using an unsupervised, competitive learning to produce a low dimensional, discretized representation (feature map) of higher dimensional data.