Quantum Circuits for Quantum Convolutions: A Quantum Convolutional Autoencoder
This work addresses the challenge of integrating quantum mechanics into machine learning for researchers in quantum computing and AI, though it appears incremental as it builds on existing quantum and classical methods.
The paper tackles the problem of processing input data in quantum machine learning by using randomized quantum circuits as quantum convolutions to generate new representations for convolutional networks, achieving performance comparable to classic convolutional neural networks and accelerating convergence in some instances.
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.