Are classical neural networks quantum?
This work addresses a foundational question in quantum physics and machine learning, potentially bridging classical and quantum computing domains.
The paper investigates whether classical neural networks possess hidden quantum properties that make them effective for approximating wavefunctions in many-particle quantum systems, concluding that neural networks can be interpreted as having quantum remnants.
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.