Machine learning enhanced quantum state tomography on a field-programmable gate array
Machine learning techniques have opened new avenues for real-time quantum state tomography (QST). In this work, we demonstrate the deployment of machine learning-based QST on edge devices, specifically utilizing field-programmable gate arrays (FPGAs). Our implementation uses the Vitis AI Integrated...
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIP Publishing LLC
2025-06-01
|
| Series: | APL Quantum |
| Online Access: | http://dx.doi.org/10.1063/5.0262942 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Machine learning techniques have opened new avenues for real-time quantum state tomography (QST). In this work, we demonstrate the deployment of machine learning-based QST on edge devices, specifically utilizing field-programmable gate arrays (FPGAs). Our implementation uses the Vitis AI Integrated Development Environment provided by AMD® Inc. Compared to graphics processing unit-based machine learning QST, our FPGA-based approach reduces the average inference time by an order of magnitude, from 38 to 2.94 ms, but only suffers an average fidelity reduction by about 1% (from 0.99 to 0.98). This FPGA-based QST system offers a highly efficient and precise tool for diagnosing quantum states, marking a significant advancement in the practical applications for quantum information processing and quantum sensing. |
|---|---|
| ISSN: | 2835-0103 |