Abstract
Self-organizing maps are extremely useful in the field of pattern recognition. They become less useful, however, when neurons fail to activate during training. This phenomenon occurs when neurons are initialized in areas of non-input and are far enough away from the input data to never move toward the input. These neurons effectively misrepresent the data set. This results in, among other things, patterns becoming unrecognizable. We introduce an algorithm called No Neuron Left Behind to solve this problem. We show that our algorithm produces a more accurate topological representation of the input space. We also show that no neuron clusters form in areas of non-input and that mapping quality of the SOM increases drastically when our algorithm is implemented. Finally, the running time of NNLB is better or comparable to classic SOM without it.