Neural network layers as parametric spans
From MaRDI portal
Publication:6406640
arXiv2208.00809MaRDI QIDQ6406640FDOQ6406640
Authors: Mattia G. Bergomi, Pietro Vertechi 
Publication date: 1 August 2022
Abstract: Properties such as composability and automatic differentiation made artificial neural networks a pervasive tool in applications. Tackling more challenging problems caused neural networks to progressively become more complex and thus difficult to define from a mathematical perspective. We present a general definition of linear layer arising from a categorical framework based on the notions of integration theory and parametric spans. This definition generalizes and encompasses classical layers (e.g., dense, convolutional), while guaranteeing existence and computability of the layer's derivatives for backpropagation.
This page was built for publication: Neural network layers as parametric spans
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6406640)
