Figure 1 - uploaded by Jun Qi
Content may be subject to copyright.
Download
View publication
An illustration of QNN based on VQC.

An illustration of QNN based on VQC.

Source publication
Figure 1: An illustration of QNN based on VQC.
Figure 2: Different paradigms for quantum embedding. (a) a dense layer...
Figure 4: A framework of variational quantum circuit.
Comparison of model performance on the MNIST test dataset.
QTN-VQC: AN END-TO-END LEARNING FRAMEWORK FOR QUANTUM NEURAL NETWORKS A PREPRINT
Preprint
Full-text available
  • Oct 2021
The advent of noisy intermediate-scale quantum (NISQ) computers raises a crucial challenge to design quantum neural networks for fully quantum learning tasks. To bridge the gap, this work proposes an end-to-end learning framework named QTN-VQC, by introducing a trainable quantum tensor network (QTN) for quantum embedding on a variational quantum ci...
Cite
Download full-text

Context in source publication

Context 1
... shown in Figure 1, our QNN builds a unitary linear operator that consists of three main components: (1) quantum embedding generation; (2) variational quantum circuit; (3) measurement. Quantum embedding generation, also known as quantum encoding, applies a fixed unitary linear operator H x transforming classical vectors x to quantum states |ψ x in a Hilbert space. ...

Similar publications

Fig. 1. [Top] Classical transfer learning: Input data, deep learning...
Fig. 3. A single-qubit N-layer QML network without data re-uploading
Fig. 4. A multi-qubit N-layer QML network with data re-uploading: L 1 ,...
Fig. 5. A multi-qubit N-layer QML network without data re-uploading: L...
+2 Fig. 6. Some examples of the large-scale UC Merced Land Use dataset...
Quantum Transfer Learning for Real-World, Small, and High-Dimensional Datasets
Preprint
Full-text available
  • Sep 2022
Quantum machine learning (QML) networks promise to have some computational (or quantum) advantage for classifying supervised datasets (e.g., satellite images) over some conventional deep learning (DL) techniques due to their expressive power via their local effective dimension. There are, however, two main challenges regardless of the promised quan...
View