Enhanced image classification via hybridizing quantum dynamics with classical neural networks

TL;DR

This paper introduces a hybrid quantum-classical neural network architecture that improves image classification by leveraging quantum many-body dynamics to enhance separability and accuracy, demonstrating potential for quantum advantage.

Contribution

The work presents a novel hybrid protocol combining classical neural networks with quantum many-body dynamics for improved image classification performance.

Findings

Quantum module enhances classification accuracy beyond classical neural networks.

Images mapped to nearly-orthogonal quantum states improve class separability.

Model evaluated successfully on multiple benchmark datasets.

Abstract

The integration of quantum computing and machine learning has emerged as a promising frontier in computational science. We present a hybrid protocol which combines classical neural networks with non-equilibrium dynamics of a quantum many-body system for image classification. This architecture leverages classical neural networks to efficiently process high-dimensional data and encode it effectively on a quantum many-body system, overcoming a challenging task towards scaled up quantum computation. The quantum module further capitalizes on the discriminative properties of many-body quantum dynamics to enhance classification accuracy. By mapping images from distinct classes to nearly-orthogonal quantum states, the system maximizes separability in the Hilbert space, enabling robust classification. We evaluate the performance of our model on several benchmark datasets with various number of features and classes. Moreover, we demonstrate the key role of the quantum module in achieving high classification accuracy which cannot be accomplished by the classical neural network alone. This showcases the potential of our hybrid protocol for achieving practical quantum advantage and paves the way for future advancements in quantum-enhanced computational techniques.