Quantum Entanglement in Deep Learning Architectures

Yoav Levine*, Or Sharir, Nadav Cohen, Amnon Shashua

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

108 Scopus citations


Modern deep learning has enabled unprecedented achievements in various domains. Nonetheless, employment of machine learning for wave function representations is focused on more traditional architectures such as restricted Boltzmann machines (RBMs) and fully connected neural networks. In this Letter, we establish that contemporary deep learning architectures, in the form of deep convolutional and recurrent networks, can efficiently represent highly entangled quantum systems. By constructing tensor network equivalents of these architectures, we identify an inherent reuse of information in the network operation as a key trait which distinguishes them from standard tensor network-based representations, and which enhances their entanglement capacity. Our results show that such architectures can support volume-law entanglement scaling, polynomially more efficiently than presently employed RBMs. Thus, beyond a quantification of the entanglement capacity of leading deep learning architectures, our analysis formally motivates a shift of trending neural-network-based wave function representations closer to the state-of-the-art in machine learning.

Original languageAmerican English
Article number065301
JournalPhysical Review Letters
Issue number6
StatePublished - 12 Feb 2019

Bibliographical note

Funding Information:
We thank Guifre Vidal, Thomas Spencer, John Imbrie, Bartlomiej Czech, Eyal Bairey, Eyal Leviatan, Miles Stoudenmire, Giuseppe Carleo, Ivan Glasser, and Lei Wang for useful discussions. This work is supported by ISF Center Grant No. 1790/12 and by the European Research Council (TheoryDL project). Nadav Cohen is a member of the Zuckerman Israeli Postdoctoral Scholars Program, and is supported by the Schmidt Foundation. Yoav Levine is supported by the Adams Fellowship Program of the Israel Academy of Sciences and Humanities.

Publisher Copyright:
© 2019 American Physical Society.


Dive into the research topics of 'Quantum Entanglement in Deep Learning Architectures'. Together they form a unique fingerprint.

Cite this