# Quantum Circuits for Quantum Convolutions: A Quantum Convolutional Autoencoder

## TL;DR

This paper introduces quantum convolutional autoencoders that utilize randomized quantum circuits for data transformation, showing potential for comparable performance and faster convergence in quantum machine learning models.

## Contribution

It proposes a novel quantum convolutional approach using randomized circuits, bridging quantum computing and convolutional neural network techniques.

## Key findings

- Quantum convolutions produce effective data representations.
- Performance comparable to classical CNNs.
- Potential for accelerated convergence in quantum models.

## Abstract

Quantum machine learning deals with leveraging quantum theory with classic machine learning algorithms. Current research efforts study the advantages of using quantum mechanics or quantum information theory to accelerate learning time or convergence. Other efforts study data transformations in the quantum information space to evaluate robustness and performance boosts. This paper focuses on processing input data using randomized quantum circuits that act as quantum convolutions producing new representations that can be used in a convolutional network. Experimental results suggest that the performance is comparable to classic convolutional neural networks, and in some instances, using quantum convolutions can accelerate convergence.