Diagrammatic summaries for neural architectures

Guy Clarke Marshall, Caroline Jay, André Freitas

Keywords: Diagrams, systems, neural network architectures, guidelines, standards

TL;DR: Diagrams are effective for communicating about ML systems and should be placed centrally within the publication process

Abstract: This paper advocates for diagrammatic summary publications for machine learning system architecture papers. We review existing diagram-centric scholarly practices, and summarise relevant studies on neural network system architecture diagrams. We subsequently propose three opportunities: Diagram guidelines, diagrammatic system summary publications, and the community creation of a formal diagram standards, which could be integrated with existing LaTeX + PDF publication processes.