HQCC: A Hybrid Quantum-Classical Classifier with Adaptive Structure
This addresses a bottleneck in Quantum Machine Learning for the NISQ era, offering a practical improvement over existing methods.
The paper tackled the problem of fixed-structure Parameterized Quantum Circuits degrading Quantum Machine Learning performance by proposing a Hybrid Quantum-Classical Classifier with adaptive optimization, achieving up to 97.12% accuracy on MNIST.
Parameterized Quantum Circuits (PQCs) with fixed structures severely degrade the performance of Quantum Machine Learning (QML). To address this, a Hybrid Quantum-Classical Classifier (HQCC) is proposed. It opens a practical way to advance QML in the Noisy Intermediate-Scale Quantum (NISQ) era by adaptively optimizing the PQC through a Long Short-Term Memory (LSTM) driven dynamic circuit generator, utilizing a local quantum filter for scalable feature extraction, and exploiting architectural plasticity to balance the entanglement depth and noise robustness. We realize the HQCC on the TensorCircuit platform and run simulations on the MNIST and Fashion MNIST datasets, achieving up to 97.12\% accuracy on MNIST and outperforming several alternative methods.