On the loss of learning capability inside an arrangement of neural networks

01/09/2020

∙

by   Ivan Arraut, et al.

∙

0

∙

share

We analyze the loss of information and the loss of learning capability inside an arrangement of neural networks. Our method is new and based on the formulation of non-unitary Bogoliubov transformations in order to connect the information between different points of the arrangement. This can be done after expanding the activation function in a Fourier series and then assuming that its information is stored inside a Quantum scalar field.