Variational Learning for Quantum Artificial Neural Networks

Year: 2021

Authors: Tacchino F., Mangini S., Barkoutsos P.K.L., Macchiavello C., Gerace D., Tavernelli I., Bajoni D.

Autors Affiliation: IBM Res Zurich, IBM Quantum, CH-8803 Ruschlikon, Switzerland; Univ Pavia, Dept Phys, I-27100 Pavia, Italy; Univ Pavia, Dept Ind & Informat Engn, I-27100 Pavia, Italy; Ist Nazl Fis Nucleare, Sez Pavia, I-27100 Pavia, Italy; Consiglio Nazl Ric Ist Nazl Ottica, I-50125 Florence, Italy.

Abstract: In the past few years, quantum computing and machine learning fostered rapid developments in their respective areas of application, introducing new perspectives on how information processing systems can be realized and programmed. The rapidly growing field of quantum machine learning aims at bringing together these two ongoing revolutions. Here, we first review a series of recent works describing the implementation of artificial neurons and feedforward neural networks on quantum processors. We then present an original realization of efficient individual quantum nodes based on variational unsampling protocols. We investigate different learning strategies involving global and local layerwise cost functions, and we assess their performances also in the presence of statistical measurement noise. While keeping full compatibility with the overall memory-efficient feedforward architecture, our constructions effectively reduce the quantum circuit depth required to determine the activation probability of single neurons upon input of the relevant data-encoding quantum states. This suggests a viable approach toward the use of quantum neural networks for pattern classification on near-term quantum hardware.

Journal/Review: IEEE TRANSACTIONS ON QUANTUM ENGINEERING

Volume: 2      Pages from: 3101110-1  to: 3101110-10

More Information: This work was supported in part by Swiss National Science Foundation under Grant 200021_179312 and by the Italian Ministry of Education, University and Research (MIUR) through the Dipartimenti di Eccellenza Program (2018-2022), Department of Physics, University of Pavia. A preliminary version of this article was presented at the 2020 IEEE International Conference on Quantum Computing and Engineering [49].
KeyWords: Artificial neural networks; supervised learning; quantum computing; quantum algorithm
DOI: 10.1109/TQE.2021.3062494

Citations: 18
data from “WEB OF SCIENCE” (of Thomson Reuters) are update at: 2025-01-12
References taken from IsiWeb of Knowledge: (subscribers only)