The word “VEXEL” currently refers to a type of raster art designed to resemble vector graphics. It is more of an informal term used to describe a design criteria for certain images and does not appear frequently in common usage. The word itself can therefore be appropriated for an unrelated field, that of a novel neural network design, specifically, the computational units for a parallel processing paradigm, referred to as “VEXAFRACTA”. The term “VEXEL” is chosen to indicate the troublesome nature of both modern neural networks as are currently used for large language models and other AI generative purposes, as well as the difficulties associated with providing a rich connectivity paradigm using sparse calculations. I must also point out that the model requires vectors in the complex plane at the very least, and that even high bit count floating point operations are still “pixelized” in that an irrational number (as an example) can only ever be approximated.