Título: "The continuous formulation of shallow neural networks as Wasserstein-type gradient flows"

 

Abstract:  It has been recently observed that the training of a single hidden layer artificial neural network can be reinterpreted as a Wasserstein gradient flow for the weights for the error functional. In the limit, as the number of parameters tends to infinity, this gives rise to a family of parabolic equations. This talk aims to discuss this relation, focusing on the associated theoretical aspects appealing to the mathematical community and providing a list of interesting open problems.

 

Enlace:   https://conectaha.csic.es/b/mar-mrf-oj9-ui0

 

Referencia: https://sma.epfl.ch/~xafernan/Documents/Fernandez-Real_Figalli_Flows_Survey.pdf