We develop graph transformer models to predict the fidelity of quantum circuits on real quantum devices.
On-device training for robust variational quantum algorithms
Robust parameter training of variational quantum algorithm
Design of Variational Quantum Algorithm Program
As a data-driven approach, NAAS holistically composes highly matched accelerator and neural architectures together with efficient compiler mapping.
We develop a graph neural network and reinforcement learning based method for analog circuit transistor sizing.
