Why Scholars Are Diagramming Neural Network Models

Research output: Contribution to journalArticlepeer-review


Complex models, such as neural networks (NNs), comprise many interrelated components. In order to represent these models, eliciting and characterising the relations between components is essential. Perhaps because of this, diagrams, as "icons of relation", are a prevalent medium for signifying complex models. Diagrams used to communicate NN architectures are currently extremely varied. The diversity in diagrammatic choices provides an opportunity to gain insight into the aspects which are being prioritised for communication and into the conceptualisations of the diagram creators.
Original languageEnglish
Number of pages8
JournalLecture Notes in Computer Science
Publication statusPublished - 1 Sep 2022
EventDiagrams 2022: 13th International Conference on the Theory and Application of Diagrams - Rome, Italy
Duration: 13 Sep 202217 Sep 2022


  • Neural networks
  • systems
  • diagrams
  • conceptual models


Dive into the research topics of 'Why Scholars Are Diagramming Neural Network Models'. Together they form a unique fingerprint.

Cite this