Hybrid Classical-Quantum Autoencoder for Anomaly Detection
| Autor: | Sakhnenko, Alona, O'Meara, Corey, Ghosh, Kumar J. B., Mendl, Christian B., Cortiana, Giorgio, Bernabé-Moreno, Juan |
|---|---|
| Rok vydání: | 2021 |
| Předmět: | |
| Zdroj: | Quantum Mach. Intell. 4, 27 (2022) |
| Druh dokumentu: | Working Paper |
| DOI: | 10.1007/s42484-022-00075-z |
| Popis: | We propose a Hybrid classical-quantum Autoencoder (HAE) model, which is a synergy of a classical autoencoder (AE) and a parametrized quantum circuit (PQC) that is inserted into its bottleneck. The PQC augments the latent space, on which a standard outlier detection method is applied to search for anomalous data points within a classical dataset. Using this model and applying it to both standard benchmarking datasets, and a specific use-case dataset which relates to predictive maintenance of gas power plants, we show that the addition of the PQC leads to a performance enhancement in terms of precision, recall, and F1 score. Furthermore, we probe different PQC Ans\"atze and analyse which PQC features make them effective for this task. Comment: 17 pages, 11 figures |
| Databáze: | arXiv |
| Externí odkaz: |
|