An Online Cellular Probabilistic Self-Organizing Map for Static and Dynamic Data Sets

In this paper, a new online cellular probabilistic self-organizing map (CPSOM) is presented. The proposed online CPSOM is derived from the batch mode soft topological vector quantization (STVQ). It requires less storage than the STVQ such that it is able to deal with much larger data sets. It converges faster than the STVQ with the same effect when the map size is relatively small, and forms more ordered topology than the STVQ when the map size is relatively large. Most of all, by tuning a parameter in the CPSOM as a forgetting factor, the CPSOM can be used not only in static data sets, but also in dynamic data sets, where the input data come in endlessly and dynamically. The online CPSOM provides more information about the assignment probability for each neuron, which proved to be very useful for unsupervised clustering of the CPSOM.