Artificial Intelligence and Machine Learning in QubiC
ORAL
Abstract
Artificial intelligence (AI) and machine learning (ML) are pivotal for the advancement of quantum computing, offering new paradigms for control and optimization. Qubit Control (QubiC) is a field-programmable gate array (FPGA) based open-source full-stack control system designed specifically for quantum computing. Within the QubiC system, we explore the application of AI and ML to enhance quantum control capabilities.
We implement a neural network model on FPGA for real-time quantum state discrimination. Additionally, we create an online learning framework on FPGA that updates the state discrimination model in situ, effectively countering qubit drift. We also develop a large language model (LLM) AI agent for automatic qubit calibration. Furthermore, we use LLM to optimize hardware description language (HDL) code for quantum applications and to generate scripts for instrument manipulation in the lab.
The AI/ML advancements in QubiC will provide a versatile toolbox, paving the way for significant progress in quantum control.
We implement a neural network model on FPGA for real-time quantum state discrimination. Additionally, we create an online learning framework on FPGA that updates the state discrimination model in situ, effectively countering qubit drift. We also develop a large language model (LLM) AI agent for automatic qubit calibration. Furthermore, we use LLM to optimize hardware description language (HDL) code for quantum applications and to generate scripts for instrument manipulation in the lab.
The AI/ML advancements in QubiC will provide a versatile toolbox, paving the way for significant progress in quantum control.
*This material is based upon work supported by the U.S. Department of Energy, Office of Science, National Quantum Information Science Research Centers, Quantum Systems Accelerator. Additional support is acknowledged from the U.S. Department of Energy, Office of Science, Advanced Scientific Computing Research Testbeds for Science program, and the Office of High Energy Physics under Contract No. DE-AC02-05CH11231.
–
Presenters
-
Yilun Xu
- Lawrence Berkeley National Laboratory