SOM Training Optimization Using Triangle Inequality.

Triangle inequality optimization is one of several strategies on the k-means algorithm that can reduce the search space in finding the nearest prototype vector. This optimization can also be applied towards Self-Organizing Maps training, particularly during finding the best matching unit in the batch training approach. This paper investigates various implementations of this optimization and measures the efficiency gained on various datasets, dimensions, maps, cluster size and density. Our experiments on synthetic and real life datasets show that the number of comparisons can be reduced to 24% and the running time can also reduced to between 63 and 87%.