This paper examines diagrams describing neural network systems in academic conference proceedings. Many aspects of scholarly communication are controlled, particularly with relation to text and for- matting, but often diagrams are not centrally curated beyond a peer review. Using a corpus-based approach, we argue that the heterogeneous diagrammatic notations used for neural network systems have implications for signification in this domain. We divide this into two questions (i) what content is being represented and (ii) how relations are encoded. Using a novel structuralist framework, we use a corpus analysis to quantitatively cluster diagrams according to the author's representational choices. This quantitative diagram classification in a heterogeneous domain may provide a foundation for categorising representational properties of diagrams.