Continuous limits of residual neural networks in case of large input data

Autor: Herty, M., Thuenen, A., Trimborn, T., Visconti, G.
Rok vydání: 2021
Předmět:
Druh dokumentu: Working Paper
Popis: Residual deep neural networks (ResNets) are mathematically described as interacting particle systems. In the case of infinitely many layers the ResNet leads to a system of coupled system of ordinary differential equations known as neural differential equations. For large scale input data we derive a mean--field limit and show well--posedness of the resulting description. Further, we analyze the existence of solutions to the training process by using both a controllability and an optimal control point of view. Numerical investigations based on the solution of a formal optimality system illustrate the theoretical findings.
Databáze: arXiv