Fragmentation; a Tool for Finding Information, Encryption and Data Flow in Systems

We introduce a new information-theoretic measure, fragmentation which can be used to determine how fragmented information is in a system. The concept can be extended to generate fragmentation matrices that can, in turn, illustrate information flows through digital brains, in the form of directed ’information flow’ graphs. In addition to introducing Fragmentation we show how it’s application can be used to better understand how digital brains process information and “think”. We show that fragmentation can be used to examine how complex processing arises in neural networks, including differences in lifetime processing and incidents of incidental encryption.