Naming Schema for a Human Brain-Scale Neural Network
This work addresses a problem for scientists in the human brain Connectome community by providing a tool to aid research on artificial neural networks that mimic brain structures, though it is incremental as it builds on existing storage and modeling capabilities.
The paper tackles the challenge of managing and understanding large-scale neural networks comparable to the human brain by proposing a naming schema to label groups of artificial neurons that parallel those in the brain, enabling specific labeling in small regions for future study.
Deep neural networks have become increasingly large and sparse, allowing for the storage of large-scale neural networks with decreased costs of storage and computation. Storage of a neural network with as many connections as the human brain is possible with current versions of the high-performance Apache Accumulo database and the Distributed Dimensional Data Model (D4M) software. Neural networks of such large scale may be of particular interest to scientists within the human brain Connectome community. To aid in research and understanding of artificial neural networks that parallel existing neural networks like the brain, a naming schema can be developed to label groups of neurons in the artificial network that parallel those in the brain. Groups of artificial neurons are able to be specifically labeled in small regions for future study.