Hybrid quantum-classical reservoir computing for simulating chaotic systems
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:G2GC3D6Srecord.jsonopen to challenge →
read the original abstract
Forecasting chaotic systems is a notably complex task, which in recent years has been approached with reasonable success using reservoir computing (RC), a recurrent network with fixed random weights (the reservoir) used to extract the spatio-temporal information of the system. This work presents a hybrid quantum reservoir-computing (HQRC) framework, which replaces the reservoir in RC with a quantum circuit. The modular structure and measurement feedback in the circuit are used to encode the complex system dynamics in the reservoir states, from which classical learning is performed to predict future dynamics. The noiseless simulations of HQRC demonstrate valid prediction times comparable to state-of-the-art classical RC models for both the Lorenz63 and double-scroll chaotic paradigmatic systems and adhere to the attractor dynamics long after the forecasts have deviated from the ground truth.
This paper has not been read by Pith yet.
Forward citations
Cited by 3 Pith papers
-
Temporal processing of quantum states with hybrid quantum-classical reservoirs
Hybrid quantum-classical reservoir computing enables nonlinear temporal processing of quantum states and outperforms pure quantum or classical reservoirs in both full-tomography and single-axis measurement regimes.
-
Harnessing quantum back-action for time-series processing
Indirect measurements in quantum reservoir computing improve execution time scaling, overall performance, and memory capacity over projective measurements and classical feedback methods.
-
Fixed-Reservoir vs Variational Quantum Architectures for Chaotic Dynamics: Benchmarking QRC and QPINN on the Lorenz System
Fixed-reservoir QRC achieves 81% lower test MSE and 52,000x faster training than variational QPINN on Lorenz chaotic prediction with 4-5 qubits.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.