A quantum information theoretic view on a deep quantum neural network

Autor(en)

Beatrix C. Hiesmayr

Abstrakt

We discuss a quantum version of an artificial deep neural network where the role of neurons is taken over by qubits and the role of weights is played by unitaries. The role of the non-linear activation function is taken over by subsequently tracing out layers (qubits) of the network. We study two examples and discuss the learning from a quantum information theoretic point of view. In detail, we show that the lower bound of the Heisenberg uncertainty relations is defining the change of the gradient descent in the learning process. We raise the question if the limit by Nature to two non-commuting observables, quantified in the Heisenberg uncertainty relations, is ruling the optimization of the quantum deep neural network. We find a negative answer.

Organisation(en)

Quantenoptik, Quantennanophysik und Quanteninformation

Journal

AIP Conference Proceedings

Band

3061

Anzahl der Seiten

9

ISSN

0094-243X

DOI

https://doi.org/10.48550/arXiv.2212.12906

Publikationsdatum

03-2024

Peer-reviewed

Ja

ÖFOS 2012

103025 Quantenmechanik

ASJC Scopus Sachgebiete

Allgemeine Physik und Astronomie

Link zum Portal

https://ucrisportal.univie.ac.at/de/publications/054ae854-4e01-4dbf-93dc-e4b8f41c60d3