A novel neural paradigm
Modern CPUs have multiple cores, thread and resource management and context switching in ways that were nearly unimaginable in the old days. But they still excel at running serial, sequential programs. GPUs, NPUs and other massively parallel processors are far better at concurrency, simultaneous processing of many small computations across large chunks of data, parallel […]
Working Summary: The VexaFracta Model VexaFracta is a proposed neural-computational substrate built around sparse, locally stateful, phase-sensitive units rather than dense, always-on layers. The central complaint is not that modern neural networks fail. Plainly, they do not. The complaint is that they succeed at enormous computational and financial cost, often by engaging far more machinery […]
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 […]