CTRQNets & LQNets: Continuous Time Recurrent and Liquid Quantum Neural Networks

TL;DR

This paper introduces CTRQNet and LQNet, innovative quantum neural network models designed to enhance dynamic learning and temporal data modeling, achieving up to 40% accuracy improvements on CIFAR-10.

Contribution

The paper presents two novel quantum neural network architectures that incorporate continuous time and liquid dynamics, addressing static limitations of prior quantum models.

Findings

Achieved up to 40% accuracy increase on CIFAR-10.

Demonstrated improved dynamic and temporal data modeling.

Showed potential for quantum machine learning interpretability.

Abstract

Neural networks have continued to gain prevalence in the modern era for their ability to model complex data through pattern recognition and behavior remodeling. However, the static construction of traditional neural networks inhibits dynamic intelligence. This makes them inflexible to temporal changes in data and unfit to capture complex dependencies. With the advent of quantum technology, there has been significant progress in creating quantum algorithms. In recent years, researchers have developed quantum neural networks that leverage the capabilities of qubits to outperform classical networks. However, their current formulation exhibits a static construction limiting the system's dynamic intelligence. To address these weaknesses, we develop a Liquid Quantum Neural Network (LQNet) and a Continuous Time Recurrent Quantum Neural Network (CTRQNet). Both models demonstrate a significant improvement in accuracy compared to existing quantum neural networks (QNNs), achieving accuracy increases as high as 40\% on CIFAR 10 through binary classification. We propose LQNets and CTRQNets might shine a light on quantum machine learning's black box.