Abstract
Self-organizing neural networks are excellent tools for data processing, pattern recognition, cluster analysis and more. SOMs provide a discretized representation of the input space to allow for more efficient processing and analysis. While neural networks have historically focused on the emulation of information processing by animal brains, analyzing the existing self-organizing paradigms has suggested that it could be possible to achieve quality results not only by emulating the human brain, but also by mimicking one of the fundamental forces of the universe-gravity. This paper features an algorithm, GORMANN, which utilizes Newton's law of universal gravitation to attract neurons to input data. The gravitational attraction of the data on the neurons produces results that are analogous to a cross between a SOM and an image processed by morphological thinning: the key features of the input are extracted and discretized. This has the effect of maintaining a topology similar to the input pattern while ignoring superfluous information. Current research has utilized morphological thinning for a variety of fields such as micro-blood vessel detection and real-world map analysis. In this paper, GORMANN is compared with the Kohonen SOM and morphological thinning on a number of 2D input patterns. We will show that GORMANN produces excellent results in very few iterations.