PyTorch implementation of Kohonen's Self-Organizing Map.
Project description
Kohonen's Self-Organizing Map (SOM)
Background
The original paper written by Teuvo Kohonen in 1990 was one of the first neural network model capable of unsupervised learning.
Out of the different implementations of the algorithm, this one follows almost entirely the original paper. The update function is defined as
where
and is the current epoch.
Also, each neuron is connected to all the other ones, hence the map is a complete graph, where is the number of neurons.
Example
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
kohonen-som-0.0.1.tar.gz
(3.2 kB
view hashes)
Built Distribution
Close
Hashes for kohonen_som-0.0.1-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 68738bb1d4e690371b85f5567e3a105571d2a48648ee1f96b2ca4bc80d6eadf6 |
|
MD5 | 0a9dc29ee8df1ccd9110e757bbcecf7a |
|
BLAKE2b-256 | e37f173802b0785d217b349fcad8838b559643a1f2b169dcdda0bdc53b208c09 |