Variational Quanvolutional Neural Networks with enhanced image encoding
Preprint
Abstract
Image classification is an important task in various machine learning applications. In recent years, a number of classification methods based on quantum machine learning and different quantum image encoding techniques have been proposed. In this paper, we study the effect of three different quantum image encoding approaches on the performance of a convolution-inspired hybrid quantum-classical image classification algorithm called quanvolutional neural network (QNN). We furthermore examine the effect of variational - i.e. trainable - quantum circuits on the classification results. Our experiments indicate that some image encodings are better suited for variational circuits. However, our experiments show as well that there is not one best image encoding, but that the choice of the encoding depends on the specific constraints of the application.Keywords
All Related Versions
This publication has 21 references indexed in Scilit:
- A quantum deep convolutional neural network for image recognitionQuantum Science and Technology, 2020
- Quanvolutional neural networks: powering image recognition with quantum circuitsQuantum Machine Intelligence, 2020
- Parameterized quantum circuits as machine learning modelsQuantum Science and Technology, 2019
- Quantum convolutional neural networksNature Physics, 2019
- Variational Quantum Circuit Model for Knowledge Graph EmbeddingAdvanced Quantum Technologies, 2019
- Quantum machine learningNature, 2017
- The theory of variational hybrid quantum-classical algorithmsNew Journal of Physics, 2016
- A variational eigenvalue solver on a photonic quantum processorNature Communications, 2014
- NEQR: a novel enhanced quantum representation of digital imagesQuantum Information Processing, 2013
- A flexible representation of quantum images for polynomial preparation, image compression, and processing operationsQuantum Information Processing, 2010