Image recognition with an adiabatic quantum computer I. Mapping to quadratic unconstrained binary optimization

TL;DR

This paper demonstrates how to formulate image recognition, a complex NP-hard AI problem, as a QUBO problem suitable for adiabatic quantum computing, paving the way for quantum-enhanced AI solutions.

Contribution

It introduces a method to map image recognition tasks onto QUBO format for adiabatic quantum computers, enabling quantum approaches to AI problems.

Findings

Formulated image recognition as a QUBO problem.

Showed compatibility with D-Wave quantum processors.

Lays groundwork for quantum AI algorithms.

Abstract

Many artificial intelligence (AI) problems naturally map to NP-hard optimization problems. This has the interesting consequence that enabling human-level capability in machines often requires systems that can handle formally intractable problems. This issue can sometimes (but possibly not always) be resolved by building special-purpose heuristic algorithms, tailored to the problem in question. Because of the continued difficulties in automating certain tasks that are natural for humans, there remains a strong motivation for AI researchers to investigate and apply new algorithms and techniques to hard AI problems. Recently a novel class of relevant algorithms that require quantum mechanical hardware have been proposed. These algorithms, referred to as quantum adiabatic algorithms, represent a new approach to designing both complete and heuristic solvers for NP-hard optimization problems. In this work we describe how to formulate image recognition, which is a canonical NP-hard AI problem, as a Quadratic Unconstrained Binary Optimization (QUBO) problem. The QUBO format corresponds to the input format required for D-Wave superconducting adiabatic quantum computing (AQC) processors.