Quantum Entanglement in Deep Learning Architectures

Yoav Levine, Or Sharir, Nadav Cohen, Amnon Shashua

Research output: Contribution to journalArticlepeer-review

Abstract

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 languageEnglish
Article number065301
JournalPhysical Review Letters
Volume122
Issue number6
DOIs
StatePublished - 12 Feb 2019
Externally publishedYes

Fingerprint

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

Cite this