Why scholars are diagramming neural network models

2021/04/30 by Guy Clarke Marshall, Marshall, Guy Clarke, Caroline Jay +3
Arts and Humanities · Neuroscience · #Artificial Intelligence (cs.AI) #Embodied and Extended Cognition #FOS: Computer and information sciences #Human-Computer Interaction (cs.HC) #Philosophy and History of Science

paper · pdf · doi:10.48550/arxiv.2104.14811

openalex publication_date 2021/04/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Related

• A Framework for Improving Scholarly Neural Network Diagrams
• Structuralist analysis for neural network system diagrams
• Neural Circuit Diagrams: Robust Diagrams for the Communication, Implementation, and Analysis of Deep Learning Architectures
• Mapping Knowledge Representations to Concepts: A Review and New Perspectives
• Iconicity in Cognition and Communication