The purpose of this tutorial is to introduce students, professionals, and researchers to the topic of the Self-Organizing Map (SOM), a type of artificial neural network used for dimensionality reduction. This tutorial requires the learner to have some basic understanding of R and high school mathematics. To understand R programming basics, the learner may refer to the spoken tutorial on R here. This tutorial contains three modules, which will incrementally teach the subject. The learner may go through the modules in any order, depending upon his/her interest and pace.
This tutorial series was created entirely from scratch using the R programming language. From the introduction to the application, each of its modules was designed uniquely by the contributors. The key feature of the tutorial is the construction of the SOM model from scratch. It encourages learning by doing as the complete code is available in the tutorial itself. The chapters present in each module highlight individual steps used for the model training to better explain the underlying algorithm. To create this series, the authors referred to various SOM implementations from NPTEL course [1], online literature [2-6], standard textbooks [7,8] and academic journals [9,10]. If the learner wishes to suggest any improvement, he/she can reach out to us at contact-r(at)fossee(dot)in.
The following individuals contributed to the creation of this tutorial -
[1] NPTEL - Lecture Series on Neural Networks and Applications by Prof.S. Sengupta, Department of Electronics and Electrical Communication Engineering, IIT Kharagpur. https://nptel.ac.in/courses/117/105/117105084/
[2] Self Organizing Map Tutorial System by Jae-Wook Ahn and Sue Yeon Syn.
http://www.pitt.edu/is2470pb/Spring05/FinalProjects/Group1a/tutorial/som.html
[3] Self Organizing Maps: Fundamentals. https://www.cs.bham.ac.uk/jxb/NN/l16.pdf
[4] Self-Organizing Map (SOM) by Jaakko Hollmen. https://users.ics.aalto.fi/jhollmen/dippa/node20.html
[5] Self-organizing Maps by Kevin Pang. https://www.cs.hmc.edu/kpang/nn/som.html
[6] Self-Organizing Maps by Sven Kruger. http://www.iikt.ovgu.de/iesk_media/Downloads/ks/computational_neuroscience/vorlesung
[7] Kohonen, T. 2012. Self-organizing maps. Springer Science & Business Media.
[8] Uoolc, A.B. Self-organizing Map Formation: Foundations of Neural Computation.
[9] Wehrens, R. and Buydens, L.M.C. 2007. Self- and Super-Organizing Maps in R: The kohonen Package. Journal of Statistical Software. 21, 5 (2007), 1–19. DOI: https://doi.org/10.18637/jss.v021.i05
[10] Wehrens, R. and Kruisselbrink, J. 2018. Flexible Self-Organizing Maps in kohonen 3.0. Journal of Statistical Software. 87, 7 (2018), 1–18. DOI: https://doi.org/10.18637/jss.v087.i07