Quantum Optical Experiments Modeled by Long Short-Term Memory
We demonstrate how machine learning is able to model experiments in quantum physics. Quantum entanglement is a cornerstone for upcoming quantum technologies, such as quantum computation and quantum cryptography. Of particular interest are complex quantum states with more than two particles and a lar...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Photonics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2304-6732/8/12/535 |
| _version_ | 1797501436026683392 |
|---|---|
| author | Thomas Adler Manuel Erhard Mario Krenn Johannes Brandstetter Johannes Kofler Sepp Hochreiter |
| author_facet | Thomas Adler Manuel Erhard Mario Krenn Johannes Brandstetter Johannes Kofler Sepp Hochreiter |
| author_sort | Thomas Adler |
| collection | DOAJ |
| description | We demonstrate how machine learning is able to model experiments in quantum physics. Quantum entanglement is a cornerstone for upcoming quantum technologies, such as quantum computation and quantum cryptography. Of particular interest are complex quantum states with more than two particles and a large number of entangled quantum levels. Given such a multiparticle high-dimensional quantum state, it is usually impossible to reconstruct an experimental setup that produces it. To search for interesting experiments, one thus has to randomly create millions of setups on a computer and calculate the respective output states. In this work, we show that machine learning models can provide significant improvement over random search. We demonstrate that a long short-term memory (LSTM) neural network can successfully learn to model quantum experiments by correctly predicting output state characteristics for given setups without the necessity of computing the states themselves. This approach not only allows for faster search, but is also an essential step towards the automated design of multiparticle high-dimensional quantum experiments using generative machine learning models. |
| first_indexed | 2024-03-10T03:18:23Z |
| format | Article |
| id | doaj.art-57b14800fbbd4dfbb904c1fa69f4617a |
| institution | Directory Open Access Journal |
| issn | 2304-6732 |
| language | English |
| last_indexed | 2024-03-10T03:18:23Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Photonics |
| spelling | doaj.art-57b14800fbbd4dfbb904c1fa69f4617a2023-11-23T10:08:32ZengMDPI AGPhotonics2304-67322021-11-0181253510.3390/photonics8120535Quantum Optical Experiments Modeled by Long Short-Term MemoryThomas Adler0Manuel Erhard1Mario Krenn2Johannes Brandstetter3Johannes Kofler4Sepp Hochreiter5ELLIS Unit Linz, LIT AI Lab, Institute for Machine Learning, Johannes Kepler University, 4040 Linz, AustriaInstitute for Quantum Optics and Quantum Information, Austrian Academy of Sciences & Vienna Center for Quantum Science & Technology, University of Vienna, 1090 Vienna, AustriaDepartment of Chemistry, University of Toronto & Vector Institute for Artificial Intelligence, Toronto, ON M5G 1M1, CanadaELLIS Unit Linz, LIT AI Lab, Institute for Machine Learning, Johannes Kepler University, 4040 Linz, AustriaELLIS Unit Linz, LIT AI Lab, Institute for Machine Learning, Johannes Kepler University, 4040 Linz, AustriaELLIS Unit Linz, LIT AI Lab, Institute for Machine Learning, Johannes Kepler University, 4040 Linz, AustriaWe demonstrate how machine learning is able to model experiments in quantum physics. Quantum entanglement is a cornerstone for upcoming quantum technologies, such as quantum computation and quantum cryptography. Of particular interest are complex quantum states with more than two particles and a large number of entangled quantum levels. Given such a multiparticle high-dimensional quantum state, it is usually impossible to reconstruct an experimental setup that produces it. To search for interesting experiments, one thus has to randomly create millions of setups on a computer and calculate the respective output states. In this work, we show that machine learning models can provide significant improvement over random search. We demonstrate that a long short-term memory (LSTM) neural network can successfully learn to model quantum experiments by correctly predicting output state characteristics for given setups without the necessity of computing the states themselves. This approach not only allows for faster search, but is also an essential step towards the automated design of multiparticle high-dimensional quantum experiments using generative machine learning models.https://www.mdpi.com/2304-6732/8/12/535quantum opticsmultipartite high-dimensional entanglementsupervised machine learninglong short-term memory |
| spellingShingle | Thomas Adler Manuel Erhard Mario Krenn Johannes Brandstetter Johannes Kofler Sepp Hochreiter Quantum Optical Experiments Modeled by Long Short-Term Memory Photonics quantum optics multipartite high-dimensional entanglement supervised machine learning long short-term memory |
| title | Quantum Optical Experiments Modeled by Long Short-Term Memory |
| title_full | Quantum Optical Experiments Modeled by Long Short-Term Memory |
| title_fullStr | Quantum Optical Experiments Modeled by Long Short-Term Memory |
| title_full_unstemmed | Quantum Optical Experiments Modeled by Long Short-Term Memory |
| title_short | Quantum Optical Experiments Modeled by Long Short-Term Memory |
| title_sort | quantum optical experiments modeled by long short term memory |
| topic | quantum optics multipartite high-dimensional entanglement supervised machine learning long short-term memory |
| url | https://www.mdpi.com/2304-6732/8/12/535 |
| work_keys_str_mv | AT thomasadler quantumopticalexperimentsmodeledbylongshorttermmemory AT manuelerhard quantumopticalexperimentsmodeledbylongshorttermmemory AT mariokrenn quantumopticalexperimentsmodeledbylongshorttermmemory AT johannesbrandstetter quantumopticalexperimentsmodeledbylongshorttermmemory AT johanneskofler quantumopticalexperimentsmodeledbylongshorttermmemory AT sepphochreiter quantumopticalexperimentsmodeledbylongshorttermmemory |