IEEE National Aerospace and Electronics Conference (NAECON)

Learning Quantum System Disturbance Models with Probabilistic Bayesian Neural Networks

Zhenhua Jiang, Linh Nguyen

Published Aug 28, 2023• 1 citation

Abstract

This paper presents a probabilistic machine learning approach that is well suited to learning unknown disturbance dynamics (which may be caused by errors, noise, and parameter variations) in quantum processes or systems from operational data using a Bayesian neural network. This approach considers the dependence of the quantum circuit fidelity (or quantum state output deviation) on the variations of parameters (or factors) such as relaxation time TI, coherence time T2, crosstalk intensity, extra decay, etc. These disturbance factors are used as input variables in the disturbance model, and the quantum circuit fidelity is the output. The respective probability distribution of the weights capturing the disturbance-to-output relationships are learnable parameters of the disturbance model and can be learned from operational data. The learning process may apply to quantify the uncertainty of disturbance in the partial system dynamics, while portions of the nominal system dynamics may be given (or learned from a separate dynamic model). The learned stochastic quantum disturbance models together with the known nominal physical models can be used in the design of quantum system optimal control. As an example, two cases about the applications of probabilistic modeling are studied to learn the noise dynamics in a particular quantum circuit based on simulated datasets. The results are analyzed in different scenarios, and a plan for future work is identified.

DOI: 10.1109/naecon58068.2023.10365822

Related papers

Probabilistic Graybox Characterization of Quantum Devices With Bayesian Neural Networks

Poramet Pathumsoot, Michal Hajdušek, Rodney Van Meter

While the Graybox characterization method allows for implicit noise models and is platform-agnostic, the method lacks uncertainty quantification. Characterization of quantum devices is a crucial process that enables researchers to gain insight from experimental settings. Graybox characterization combines known system dynamics with unknown transformations, where the latter is modeled using machine learning. Prediction uncertainty helps researchers make informed decisions. It allows valuable insights from the devices without overconfidence. We therefore develop a probabilistic Graybox characterization model using probabilistic machine learning, specifically Bayesian Neural Networks, and utilize binary measurement outcomes directly for inference. With stochastic noise in a quantum device, we analyze statistical properties of the measurement data. Our results show that the model's prediction performance solely depends on its ability to capture the expected value of the true expectation value. Our proposed probabilistic Graybox model outperforms the original model by up to 1.9 times in capturing the distribution of observed data. We expect that our results will serve as an additional tool for characterizing quantum devices with uncertainty estimation, as they provide a flexible choice that can be utilized even without extensive prior knowledge of the noise model of the devices.

arXiv:2509.24232IEEE Transactions on Quantum EngineeringJan 1, 20260 citations

Quantum-Aided Bayesian Learning for the Prediction and Uncertainty Quantification of Remaining Useful Life

Giorgio Tosti Balducci, Nick Eleftheroglou

To make predictions on the future states of engineering systems, prognostics has been increasingly relying on data-driven models and machine learning. Recent work has also looked at the potential of quantum machine learning to provide insight on the health state of systems. Nevertheless, these approaches treated the quantum component only as a deterministic predictor, in fact disregarding the uncertainty information. In this work, we propose a different approach to exploiting quantum circuits in prognostics. We focus on Bayesian learning of neural networks for Remaining Useful Life (RUL) prediction and uncertainty quantification. Here, the quantum circuit is introduced not as a data-driven model, but as a generator of neural network weights. Using Variational Inference, the quantum circuit can be trained to approximate the true posterior of the classical machine learning predictor. The overall method retains the data-processing ability of state-of-the-art machine learning models, while exploiting the quantum circuit to introduce uncertainty by sampling the modelspace from a distribution that is classically nontrivial. We validate our approach on the task of predicting the End of Discharge of Li-ion batteries, using data generated from a simulator with tunable process uncertainty, and we compare the predictions obtained through quantum sampling with those from Flipout Bayesian neural networks, heteroscedastic neural networks and Monte Carlo Dropout. The results show that our quantum circuits learn to approximate the weight posterior and that the resulting data-driven models demonstrate accuracy and uncertainty quantification that is comparable if not superior to the baselines. Overall, our work demonstrates the potential of quantum computing for uncertainty-aware prognostics, and sets the stage for further investigations in this area.

PHM Society European ConferenceJul 3, 20260 citations

QuProbLeM - A Novel Quantum Probabilistic Learning Machine: Software Architecture

Zhenhua Jiang, Linh Nguyen

This paper presents a novel Quantum Probabilistic Learning Machine (QuProbLeM) paradigm that is fully based on Bayesian inference and well suited to directly learning the patterns or correlations inherent in dynamic processes from operation data by using a probabilistic neural network. In the QuProbLeM, the respective probability distributions of the weights capturing the input-to-output relationships are learnable parameters that can be learned from data samples. This revolutionary machine learning (ML) paradigm is inspired by the philosophy of Parts and the Total (e.g., each part, or data sample, in a closed system affects the total in such a way that the whole system will thereafter influence every single part). This first-of-the-type probabilistic learning machine can be effectively implemented on a quantum computing system that may also share the same philosophy naturally. The proposed QuProbLeM solver can take as its input a set of quantum-encoded data samples comprising pairs of cause-effect variables, and its output may include the updated probability distributions of the model's parameters (i.e., weights) and the predicted effect (output) variables and their distributions when given new cause (input) variables or their distributions. Alternatively, classical data can be first fed into a front-end Bayesian learning network to initially learn the probability distributions of the cause-effect variable pairs and then encoded into coherent quantum states as the input. Uniquely, the QuProbLeM solver directly computes probability distributions of the learning network's weights in an inference-based, entangled manner (but not iteratively as in traditional ML), by synthesizing the quantum training datasets, inferring about the model fidelity and updating the weight's probabilities based on inverse quantum operations.

IEEE National Aerospace and Electronics Conference (NAECON)Jul 15, 20241 citation

Quantum neural networks for machine learning applied to the tracking and control of the dynamics of stochastic transmission lines

Harish Parthasarathy, Arti Vaish

In most of the machine learning problems based on classical neural networks, we try to identify a nonlinear system which may or may not have memory by adapting the weights of the neural network so that for the same input process applied to the system as well as to the neural network, the network output matches that of the true system output in the mean square sense or in the sense of some other metric on the space of output processes. If the network is feed forward, then this model can be used to simulate a memory-less nonlinear system. If however the actual system has memory and is described by a stochastic difference equation for its state followed by an output equation that is a function of the state, then we can use a recurrent neural network (RNN) whose state dynamics are described by a nonlinear difference equation involving weights as parameters and the state and weights of the RNN can be estimated from noisy measurements of the actual system output by means of the extended Kalman filter. If however, we are interested in estimating the joint probability density of a vector valued process like the transmission line current and voltage at different points along the line at all times, then a classical neural network will not work. This is because a probability density has several constraints like non-negativity and integrability to unity, and so on, and a classical neural network does not take care of these constraints.

CRC Press eBooksAug 18, 20231 citation

Machine learning classification of non-Markovian noise disturbing quantum dynamics

Stefano Martina, Stefano Gherardini, Filippo Caruso

Abstract In this paper machine learning and artificial neural network models are proposed for the classification of external noise sources affecting a given quantum dynamics. For this purpose, we train and then validate support vector machine, multi-layer perceptron and recurrent neural network models with different complexity and accuracy, to solve supervised binary classification problems. As a result, we demonstrate the high efficacy of such tools in classifying noisy quantum dynamics using simulated data sets from different realizations of the quantum system dynamics. In addition, we show that for a successful classification one just needs to measure, in a sequence of discrete time instants, the probabilities that the analysed quantum system is in one of the allowed positions or energy configurations. Albeit the training of machine learning models is here performed on synthetic data, our approach is expected to find application in experimental schemes, as e.g. for the noise benchmarking of noisy intermediate-scale quantum devices.

arXiv:2101.03221Physica ScriptaJan 16, 202312 citations

An introduction to Bayesian simulation-based inference for quantum machine learning with examples

Ivana Nikoloska, Osvaldo Simeone

Simulation is an indispensable tool in both engineering and the sciences. In simulation-based modeling, a parametric simulator is adopted as a mechanistic model of a physical system. The problem of designing algorithms that optimize the simulator parameters is the focus of the emerging field of simulation-based inference (SBI), which is often formulated in a Bayesian setting with the goal of quantifying epistemic uncertainty. This work studies Bayesian SBI that leverages a parameterized quantum circuit (PQC) as the underlying simulator. The proposed solution follows the well-established principle that quantum computers are best suited for the simulation of certain physical phenomena. It contributes to the field of quantum machine learning by moving beyond the likelihood-based methods investigated in prior work and accounting for the likelihood-free nature of PQC training. Experimental results indicate that well-motivated quantum circuits that account for the structure of the underlying physical system are capable of simulating data from two distinct tasks.

Frontiers in Quantum Science and TechnologyAug 29, 20241 citation