Abstract
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 language | English |
|---|---|
| Number of pages | 8 |
| Journal | Lecture Notes in Computer Science |
| Publication status | Published - 1 Sept 2022 |
| Event | Diagrams 2022: 13th International Conference on the Theory and Application of Diagrams - Rome, Italy Duration: 13 Sept 2022 → 17 Sept 2022 http://www.diagrams-conference.org/2022/ |
Keywords
- Neural networks
- systems
- diagrams
- conceptual models