I. Introduction
A Self-Organising Map (SOM) neural network is an unsupervised algorithm widely used for applications that require data dimensionality reduction and clustering [1], [2]. According to [3], application areas such as medical, telecommunications, robotics, Internet of Things (IoT), video and image processing are among those that use SOM. However, the complexity of SOM training phase and the large amount of data necessary, make SOM implementations difficult for high processing speed applications [4], [5].