Abstract
We utilise VisDNA as a tool for understanding neural network system architecture diagrams. Through examples from scholarly proceedings, we find that the application of the framework to this ecological and complex domain is effective for reflecting on these diagrams. We argue for additional vocabulary to describe semiotic variability and internal inconsistency or misuse of visual encoding principles in diagrams. Further, for application to system diagrams, we propose the addition of “Grouping by Object” as a new visual encoding principle, and “Emphasising” as a new visual encoding type.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Blackwell, A., Green, T.: Notational systems-the cognitive dimensions of notations framework. In: HCI Models, Theories, and Frameworks: Toward an Interdisciplinary Science. Morgan Kaufmann, San Francisco (2003)
Cheng, P.C.-H.: What constitutes an effective representation? In: Jamnik, M., Uesaka, Y., Elzer Schwartz, S. (eds.) Diagrams 2016. LNCS (LNAI), vol. 9781, pp. 17–31. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-42333-3_2
Engelhardt, Y., Richards, C.: A framework for analyzing and designing diagrams and graphics. In: Chapman, P., Stapleton, G., Moktefi, A., Perez-Kriz, S., Bellucci, F. (eds.) Diagrams 2018. LNCS (LNAI), vol. 10871, pp. 201–209. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-91376-6_20
Goodfellow, I., Bengio, Y., Courville, A., Bengio, Y.: Deep Learning. MIT press, Cambridge (2016)
Hegarty, M.: The cognitive science of visual-spatial displays: implications for design. Topics Cogn. Sci. 3(3), 446–474 (2011)
Lebanoff, L., et al.: Scoring sentence singletons and pairs for abstractive summarization. arXiv preprint arXiv:1906.00077 (2019)
Marshall, G.C., Jay, C., Freitas, A.: Understanding scholarly natural language processing system diagrams through application of the Richards-Engelhardt framework. arXiv preprint arXiv:2008.11785 (2020)
Moody, D.: The “physics’’ of notations: toward a scientific basis for constructing visual notations in software engineering. IEEE Trans. Softw. Eng. 35(6), 756–779 (2009)
Richards, C., Engelhardt, Y.: The DNA of information design for charts and diagrams. Inf. Des. J. 25(3), 277–292 (2019)
Wertheimer, M.: Untersuchungen zur Lehre von der Gestalt. II. Psychologische Forschung 4(1), 301–350 (1923). https://doi.org/10.1007/BF00410640
Acknowledgement
The authors would like to thank Clive Richards and Yuri Engelhardt for useful discussions about VisDNA, and anonymous reviewers for their feedback on an earlier version of this paper.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Marshall, G.C., Jay, C., Freitas, A. (2021). Understanding Scholarly Neural Network System Diagrams Through Application of VisDNA. In: Basu, A., Stapleton, G., Linker, S., Legg, C., Manalo, E., Viana, P. (eds) Diagrammatic Representation and Inference. Diagrams 2021. Lecture Notes in Computer Science(), vol 12909. Springer, Cham. https://doi.org/10.1007/978-3-030-86062-2_39
Download citation
DOI: https://doi.org/10.1007/978-3-030-86062-2_39
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-86061-5
Online ISBN: 978-3-030-86062-2
eBook Packages: Computer ScienceComputer Science (R0)