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.
翻译:复杂的模型,如神经网络(NNs),由许多相互关联的组成部分组成。为了代表这些模型,必须引导和描述各组成部分之间的关系。也许由于这个原因,图表,作为“关系之共体”是表明复杂模型的常用媒介。用于传播NN结构的图表目前差异极大。图表选择的多样性为深入了解通信的优先方面提供了机会。在对NNP图表的哲学探索中,我们综合了概念模型、通信理论和准理论的理论。