Abstract
Classification and knowledge extraction from complex spatio-temporal brain data such as EEG or fMRI is a complex challenge. A novel architecture named the NeuCube has been established in prior literature to address this. A number of key points in the implementation of this framework, including modular design, extensibility, scalability, the source of the biologically inspired spatial structure, encoding, classification, and visualisation tools must be considered. A Python version of this framework that conforms to these guidelines has been implemented.