Efficient Quantum Feature Extraction for CNN-based Learning

01/04/2022
by   Tong Dou, et al.
18

Recent work has begun to explore the potential of parametrized quantum circuits (PQCs) as general function approximators. In this work, we propose a quantum-classical deep network structure to enhance classical CNN model discriminability. The convolutional layer uses linear filters to scan the input data. Moreover, we build PQC, which is a more potent function approximator, with more complex structures to capture the features within the receptive field. The feature maps are obtained by sliding the PQCs over the input in a similar way as CNN. We also give a training algorithm for the proposed model. The hybrid models used in our design are validated by numerical simulation. We demonstrate the reasonable classification performances on MNIST and we compare the performances with models in different settings. The results disclose that the model with ansatz in high expressibility achieves lower cost and higher accuracy.

READ FULL TEXT

page 1

page 4

page 7

page 8

page 9

research
12/16/2013

Network In Network

We propose a novel deep network structure called "Network In Network" (N...
research
04/07/2021

Quantum Enhanced Filter: QFilter

Convolutional Neural Networks (CNN) are used mainly to treat problems wi...
research
08/31/2022

Classical-to-quantum convolutional neural network transfer learning

Machine learning using quantum convolutional neural networks (QCNNs) has...
research
09/07/2021

ICCAD Special Session Paper: Quantum-Classical Hybrid Machine Learning for Image Classification

Image classification is a major application domain for conventional deep...
research
06/18/2020

Quantum algorithm for training nonlinear SVMs in almost linear time

We propose a quantum algorithm for training nonlinear support vector mac...
research
05/22/2018

Quantum classification of the MNIST dataset via Slow Feature Analysis

Quantum machine learning carries the promise to revolutionize informatio...
research
06/29/2022

Two-Stage COVID19 Classification Using BERT Features

We propose an automatic COVID1-19 diagnosis framework from lung CT-scan ...

Please sign up or login with your details

Forgot password? Click here to reset