Input-output optics as a causal time series mapping: A generative machine learning solution
The response of many-body quantum systems to an optical pulse can be extremely challenging to model. Here we explore the use of neural networks, both traditional and generative, to learn and thus simulate the response of such a system from data. The quantum system can be viewed as performing a compl...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
American Physical Society
2025-04-01
|
| Series: | Physical Review Research |
| Online Access: | http://doi.org/10.1103/PhysRevResearch.7.023015 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849734624793591808 |
|---|---|
| author | Abhijit Sen Bikram Keshari Parida Kurt Jacobs Denys I. Bondar |
| author_facet | Abhijit Sen Bikram Keshari Parida Kurt Jacobs Denys I. Bondar |
| author_sort | Abhijit Sen |
| collection | DOAJ |
| description | The response of many-body quantum systems to an optical pulse can be extremely challenging to model. Here we explore the use of neural networks, both traditional and generative, to learn and thus simulate the response of such a system from data. The quantum system can be viewed as performing a complex mapping from an input time series (the optical pulse) to an output time-series (the systems response), which is often also an optical pulse. Using both the transverse and nonintegrable Ising models as examples, we show that not only can temporal convolutional networks capture the input/output mapping generated by the system but can also be used to characterize the complexity of the mapping. This measure of complexity is provided by the size of the smallest latent space that is able to accurately model the mapping. We further find that a generative model, in particular a variational autoencoder, significantly outperforms traditional autoencoders at learning the complex response of many-body quantum systems. For the example that generated the most complex mapping, the variational autoencoder produces outputs that have less than 10% error for more than 90% of inputs across our test data. |
| format | Article |
| id | doaj-art-e02efe2bc82c49098a09a5c5c3a03e29 |
| institution | DOAJ |
| issn | 2643-1564 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | American Physical Society |
| record_format | Article |
| series | Physical Review Research |
| spelling | doaj-art-e02efe2bc82c49098a09a5c5c3a03e292025-08-20T03:07:44ZengAmerican Physical SocietyPhysical Review Research2643-15642025-04-017202301510.1103/PhysRevResearch.7.023015Input-output optics as a causal time series mapping: A generative machine learning solutionAbhijit SenBikram Keshari ParidaKurt JacobsDenys I. BondarThe response of many-body quantum systems to an optical pulse can be extremely challenging to model. Here we explore the use of neural networks, both traditional and generative, to learn and thus simulate the response of such a system from data. The quantum system can be viewed as performing a complex mapping from an input time series (the optical pulse) to an output time-series (the systems response), which is often also an optical pulse. Using both the transverse and nonintegrable Ising models as examples, we show that not only can temporal convolutional networks capture the input/output mapping generated by the system but can also be used to characterize the complexity of the mapping. This measure of complexity is provided by the size of the smallest latent space that is able to accurately model the mapping. We further find that a generative model, in particular a variational autoencoder, significantly outperforms traditional autoencoders at learning the complex response of many-body quantum systems. For the example that generated the most complex mapping, the variational autoencoder produces outputs that have less than 10% error for more than 90% of inputs across our test data.http://doi.org/10.1103/PhysRevResearch.7.023015 |
| spellingShingle | Abhijit Sen Bikram Keshari Parida Kurt Jacobs Denys I. Bondar Input-output optics as a causal time series mapping: A generative machine learning solution Physical Review Research |
| title | Input-output optics as a causal time series mapping: A generative machine learning solution |
| title_full | Input-output optics as a causal time series mapping: A generative machine learning solution |
| title_fullStr | Input-output optics as a causal time series mapping: A generative machine learning solution |
| title_full_unstemmed | Input-output optics as a causal time series mapping: A generative machine learning solution |
| title_short | Input-output optics as a causal time series mapping: A generative machine learning solution |
| title_sort | input output optics as a causal time series mapping a generative machine learning solution |
| url | http://doi.org/10.1103/PhysRevResearch.7.023015 |
| work_keys_str_mv | AT abhijitsen inputoutputopticsasacausaltimeseriesmappingagenerativemachinelearningsolution AT bikramkeshariparida inputoutputopticsasacausaltimeseriesmappingagenerativemachinelearningsolution AT kurtjacobs inputoutputopticsasacausaltimeseriesmappingagenerativemachinelearningsolution AT denysibondar inputoutputopticsasacausaltimeseriesmappingagenerativemachinelearningsolution |