PlumX Metrics
Embed PlumX Metrics

A Degressive Quantum Convolutional Neural Network and for Quantum State Classification and Code Recognition

SSRN, ISSN: 1556-5068
2023
  • 0
    Citations
  • 132
    Usage
  • 0
    Captures
  • 0
    Mentions
  • 0
    Social Media
Metric Options:   Counts1 Year3 Year

Metrics Details

  • Usage
    132
    • Abstract Views
      122
    • Downloads
      10

Article Description

With the rapid development of quantum computing, a variety of quantum convolutional neural network (QCNN) are proposed. However, only 1 features of a n-qubits input are transferred to next layer in quantum pooling layer, which results in the accuracy reduction of QCNN. To solve this problem, a novel QCNN model with a degressive circuit in quantum pooling layer is proposed. In order to enhance the ability of extracting global features, we remove the parameters sharing strategy in quantum convolutional layer, and design a quantum convolutional kernel with global eyesight. In addition, to prevent a sharp feature reduction, a degressive parameterized quantum circuit is used to construct the pooling layer. Specifically, in each pooling layer, the Z-basis measurement is only performed on the first qubit to control the rotation gate on other qubits. Compared with the state-ofthe-art model, i.e., HQCNN, the accuracy of our model increased by 0.9%, 1% and 3% respectively in three tasks: quantum state classification, binary code recognition and quaternary code recognition.

Provide Feedback

Have ideas for a new metric? Would you like to see something else here?Let us know