Improved PLSOM algorithm *Applied Intelligence* In Applied Intelligence, Vol. 32, No. 1. (2010), pp. 122-130, doi:10.1007/s10489-008-0138-7 by Erik Berglund

@article{berglund-2010, abstract = {The original {Parameter-Less} {Self-Organising} Map ({PLSOM}) algorithm was introduced as a solution to the problems the {Self-Organising} Map ({SOM}) encounters when dealing with certain types of mapping tasks. Unfortunately the {PLSOM} suffers from over-sensitivity to outliers and over-reliance on the initial weight distribution. The {PLSOM2} algorithm is introduced to address these problems with the {PLSOM}. {PLSOM2} is able to cope well with outliers without exhibiting the problems associated with the standard {PLSOM} algorithm. The {PLSOM2} requires very little computational overhead compared to the standard {PLSOM}, thanks to an efficient method of approximating the diameter of the inputs, and does not rely on a priori knowledge of the training input space. This paper provides a discussion of the reasoning behind the {PLSOM2} and experimental results showing its effectiveness for mapping tasks.}, author = {Berglund, Erik}, booktitle = {Applied Intelligence}, citeulike-article-id = {3646834}, citeulike-linkout-0 = {http://dx.doi.org/10.1007/s10489-008-0138-7}, citeulike-linkout-1 = {http://www.springerlink.com/content/t415hqw182413125}, citeulike-linkout-2 = {http://link.springer.com/article/10.1007/s10489-008-0138-7}, doi = {10.1007/s10489-008-0138-7}, journal = {Applied Intelligence}, keywords = {ann, learning, parameters, plsom, som, unsupervised-learning}, number = {1}, pages = {122--130}, posted-at = {2014-12-19 14:46:30}, priority = {2}, publisher = {Springer US}, title = {Improved {PLSOM} algorithm}, url = {http://dx.doi.org/10.1007/s10489-008-0138-7}, volume = {32}, year = {2010} }

See the CiteULike entry for more info, PDF links, BibTex etc.

In SOM learning, shrinking of the neighborhood size and decreasing update strength usually follow predefined schedules i.e. they only depend on the update step.⇒

In the PLSOM algorithm, update strength depends on the difference between a data point and the best-matching unit's weight vector, the quantization error. A large distance, indicating a bad representation of that data point in the SOM, leads to a stronger update than a small distance. The distance is scaled relative to the largest quantization error encountered so far.⇒

PLSOM reduces the number of parameters of the SOM algorithm from four to two.⇒

PLSOM overreacts to outliers: data points which are very unrepresentative of the data in general will change the network more strongly than they should.⇒

PLSOM2 addresses the problem of PLSOM overreacting to outliers.⇒