Fast Self-Organizing Maps Training

Self-organizing maps are an unsupervised machine learning technique that offers interpretable results by identifying topological properties in high-dimensional datasets and projecting them on a 2-dimensional grid. An important problem of self-organizing maps is the computational expensiveness of their training phase. In this paper, we propose a fast approach to train self-organizing maps. The approach consists of 2 steps. First, a small map identifies the most relevant areas from the entire high-dimensional input space. Then a larger map (initialized from the small one) is fine-tuned to further explore the local areas identified in the first step. The resulting map has performance (measured in terms of accuracy and quantization error) on par with self-organizing maps trained with the standard approach, but with a significantly reduced training time.

[1]  Mu-Chun Su,et al.  Improving the Self-Organizing Feature Map Algorithm Using an Efficient Initialization Scheme , 2002 .

[2]  Andreas Luch,et al.  Cell shape characterization and classification with discrete Fourier transforms and self‐organizing maps , 2018, Cytometry. Part A : the journal of the International Society for Analytical Cytology.

[3]  Esa Alhoniemi,et al.  SOM Toolbox for Matlab 5 , 2000 .

[4]  Usha A. Kumar,et al.  Comparative analysis of SOM neural network with K-means clustering algorithm , 2010, 2010 IEEE International Conference on Management of Innovation & Technology.

[5]  S. P. Lloyd,et al.  Least squares quantization in PCM , 1982, IEEE Trans. Inf. Theory.

[6]  F. Moura-Pires,et al.  Training a self-organizing map distributed on a PVM network , 1998, 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227).

[7]  Li-Chiu Chang,et al.  Exploring the spatio-temporal interrelation between groundwater and surface water by using the self-organizing maps , 2018 .

[8]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[9]  Yves Lechevallier,et al.  Clustering Large, Multi-level Data Sets: An Apporach Based on Kohonen Self Organizing Maps , 2000, PKDD.

[10]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[11]  Roland Vollgraf,et al.  Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms , 2017, ArXiv.

[12]  Charles Elkan,et al.  Using the Triangle Inequality to Accelerate k-Means , 2003, ICML.

[13]  Mu-Chun Su,et al.  Fast self-organizing feature map algorithm , 2000, IEEE Trans. Neural Networks Learn. Syst..

[14]  J. Frieman,et al.  Phenotypic redshifts with self-organizing maps: A novel method to characterize redshift distributions of source galaxies for weak lensing , 2019, Monthly Notices of the Royal Astronomical Society.

[15]  Carlos Dafonte,et al.  A distributed learning algorithm for Self-Organizing Maps intended for outlier analysis in the GAIA - ESA mission , 2015, IFSA-EUSFLAT.

[16]  Alex Krizhevsky,et al.  Learning Multiple Layers of Features from Tiny Images , 2009 .

[17]  Teuvo Kohonen,et al.  The self-organizing map , 1990, Neurocomputing.