Earth Engine is introducing
noncommercial quota tiers to safeguard shared compute resources and ensure reliable performance for everyone. All noncommercial projects will need to select a quota tier by
April 27, 2026 or will use the Community Tier by default. Tier quotas will take effect for all projects (regardless of tier selection date) on
April 27, 2026.
Learn more.
ee.Clusterer.wekaLVQ
Stay organized with collections
Save and categorize content based on your preferences.
A Clusterer that implements the Learning Vector Quantization algorithm. For more details, see:
T. Kohonen, "Learning Vector Quantization", The Handbook of Brain Theory and Neural Networks, 2nd Edition, MIT Press, 2003, pp. 631-634.
| Usage | Returns | ee.Clusterer.wekaLVQ(numClusters, learningRate, epochs, normalizeInput) | Clusterer |
| Argument | Type | Details | numClusters | Integer, default: 7 | The number of clusters. |
learningRate | Float, default: 1 | The learning rate for the training algorithm. Value should be greater than 0 and less or equal to 1. |
epochs | Integer, default: 1000 | Number of training epochs. Value should be greater than or equal to 1. |
normalizeInput | Boolean, default: false | Skip normalizing the attributes. |
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.
Last updated 2024-09-19 UTC.
[null,null,["Last updated 2024-09-19 UTC."],[],["The `ee.Clusterer.wekaLVQ` function implements the Learning Vector Quantization algorithm for clustering. It requires specifying the number of clusters (`numClusters`, default 7), the learning rate (`learningRate`, default 1, between 0 and 1), the number of training epochs (`epochs`, default 1000, at least 1), and whether to normalize the input attributes (`normalizeInput`, default false). The function returns a Clusterer object. The algorithm's details are described in a specific paper by T. Kohonen.\n"]]