Simultaneous Quantum Machine Learning Training and Architecture Discovery

TL;DR

This paper introduces a novel quantum machine learning algorithm that simultaneously learns both the architecture and parameters of a gated quantum system, addressing a key open question in the field.

Contribution

It presents the first algorithm capable of concurrently discovering quantum machine learning architectures and optimizing their parameters.

Findings

Algorithm successfully learns quantum architectures and parameters

Exploration of variations demonstrates flexibility

Proof of concept validates approach

Abstract

With the onset of gated quantum machine learning, the architecture for such a system is an open question. Many architectures are created either ad hoc or are directly analogous from known classical architectures. Presented here is a novel algorithm which learns a gated quantum machine learning architecture while simultaneously learning its parameters. This proof of concept and some of its variations are explored and discussed.