Why scholars are diagramming neural network models
Human-Computer Interaction
2022-06-13 v2 Artificial Intelligence
Abstract
Complex models, such as neural networks (NNs), are comprised of 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. In this philosophical exploration of NN diagrams, we integrate theories of conceptual models, communication theory, and semiotics.
Cite
@article{arxiv.2104.14811,
title = {Why scholars are diagramming neural network models},
author = {Guy Clarke Marshall and Caroline Jay and Andre Freitas},
journal= {arXiv preprint arXiv:2104.14811},
year = {2022}
}
Comments
16 pages, 4 figures