Parametrized quantum circuit anomaly detector trained on classical hardware and tested on IBM devices for handwritten digits and simulated long-lived particle signals in HEP, but does not outperform classical deep neural networks due to noise and amplitude encoding requirements.
url: https://arxiv.org/abs/2006.12270
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
quant-ph 2verdicts
UNVERDICTED 2representative citing papers
Quantum convolutional autoencoders are adapted for reconstruction-based anomaly detection on time-series data, with a bottleneck architecture suggested to outperform hierarchical ones on an exoplanet dataset.
citing papers explorer
-
Long-lived Particles Anomaly Detection with Parametrized Quantum Circuits
Parametrized quantum circuit anomaly detector trained on classical hardware and tested on IBM devices for handwritten digits and simulated long-lived particle signals in HEP, but does not outperform classical deep neural networks due to noise and amplitude encoding requirements.
-
Quantum Convolutional Autoencoders for Reconstruction-Based Anomaly Detection
Quantum convolutional autoencoders are adapted for reconstruction-based anomaly detection on time-series data, with a bottleneck architecture suggested to outperform hierarchical ones on an exoplanet dataset.