Learning Nonlinear Input-Output Maps with Dissipative Quantum Systems

Abstract

In this paper, we develop a theory of learning nonlinear input-output maps with fading memory by dissipative quantum systems, as a quantum counterpart of the theory of approximating such maps using classical dynamical systems. The theory identifies the properties required for a class of dissipative quantum systems to be {\em universal}, in that any input-output map with fading memory can be approximated arbitrarily closely by an element of this class. We then introduce an example class of dissipative quantum systems that is provably universal. Numerical experiments illustrate that with a small number of qubits, this class can achieve comparable performance to classical learning schemes with a large number of tunable parameters. Further numerical analysis suggests that the exponentially increasing Hilbert space presents a potential resource for dissipative quantum systems to surpass classical learning schemes for input-output maps.

33 pages, 12 figures, 2 tables. Close to published version in Quantum Information Processing (https://rdcu.be/bCBUf)

References in corpus (5)

• Quantum Circuit Learning
• Classical simulation of commuting quantum computations implies collapse of the polynomial hierarchy
• Boosting computational power through spatial multiplexing in quantum reservoir computing
• Qubit models of weak continuous measurements
• A discrete invitation to quantum filtering and feedback control

Cited by in corpus (22)

• Quantum reservoir computing with a single nonlinear oscillator
• Dynamical phase transitions in quantum reservoir computing
• Temporal Information Processing on Noisy Quantum Computers
• Gaussian states of continuous-variable quantum systems provide universal and versatile reservoir computing
• Information Processing Capacity of Spin-Based Quantum Reservoir Computing Systems
• Learning temporal data with variational quantum recurrent neural network
• Dissipation as a resource for Quantum Reservoir Computing
• Learning Temporal Quantum Tomography
• Quantum reservoir computing in finite dimensions
• Harnessing Quantum Extreme Learning Machines for image classification
• Superpolynomial Quantum Enhancement in Polaritonic Neuromorphic Computing
• Role of coherence in many-body Quantum Reservoir Computing
• Benchmarking the role of particle statistics in Quantum Reservoir Computing
• Practical Few-Atom Quantum Reservoir Computing
• Stochastic Reservoir Computers
• Quantum Reservoir Computing for Speckle-Disorder Potentials
• Liouvillian skin effect in quantum neural networks
• Universal Approximation Theorem and error bounds for quantum neural networks and quantum reservoirs
• Predicting three-dimensional chaotic systems with four qubit quantum systems
• Feedback Connections in Quantum Reservoir Computing with Mid-Circuit Measurements
• Quantum reservoir computing for predicting and characterizing chaotic maps
• Practical Quantum Reservoir Computing in Rydberg Atom Arrays