Are classical neural networks quantum?

TL;DR

This paper explores whether classical neural networks possess hidden quantum properties that contribute to their effectiveness in modeling complex quantum systems, questioning the classical-quantum boundary in neural network applications.

Contribution

The paper investigates the quantum-like features of classical neural networks and their role in approximating quantum states, providing insights into their suitability for quantum problem-solving.

Findings

Classical neural networks can exhibit quantum-like properties.

Neural networks effectively approximate quantum wavefunctions.

Potential quantum remnants in classical models enhance their performance.

Abstract

Neural networks are being used to improve the probing of the state spaces of many particle systems as approximations to wavefunctions and in order to avoid the recurring sign problem of quantum monte-carlo. One may ask whether the usual classical neural networks have some actual hidden quantum properties that make them such suitable tools for a highly coupled quantum problem. I discuss here what makes a system quantum and to what extent we can interpret a neural network as having quantum remnants.