Structuralist analysis for neural network system diagrams

TL;DR

This paper introduces a structuralist framework to analyze and classify neural network system diagrams in academic publications, revealing implications of diverse notations for scholarly communication.

Contribution

It presents a novel corpus-based structuralist approach to categorize neural network diagrams based on representational choices, aiding future analysis of diagrammatic heterogeneity.

Findings

Diagrams vary significantly in content and relation encoding.

Quantitative clustering reveals distinct diagrammatic styles.

Framework supports systematic analysis of scholarly diagrams.

Abstract

This short paper examines diagrams describing neural network systems in academic conference proceedings. Many aspects of scholarly communication are controlled, particularly with relation to text and formatting, but often diagrams are not centrally curated beyond a peer review. Using a corpus-based approach, we argue that the heterogeneous diagrammatic notations used for neural network systems has implications for signification in this domain. We divide this into (i) what content is being represented and (ii) how relations are encoded. Using a novel structuralist framework, we use a corpus analysis to quantitatively cluster diagrams according to the author's representational choices. This quantitative diagram classification in a heterogeneous domain may provide a foundation for further analysis.