eXplainable AI for Quantum Machine Learning
- URL: http://arxiv.org/abs/2211.01441v1
- Date: Wed, 2 Nov 2022 19:20:56 GMT
- Title: eXplainable AI for Quantum Machine Learning
- Authors: Patrick Steinm\"uller and Tobias Schulz and Ferdinand Graf and Daniel
Herr
- Abstract summary: Parametrized Quantum Circuits (PQCs) enable a novel method for machine learning (ML)
We will discuss the performance of established xAI methods, such as Baseline SHAP and Integrated Gradients.
Using the internal mechanics of PQCs we study ways to speed up their computation.
- Score: 29.117546724364857
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Parametrized Quantum Circuits (PQCs) enable a novel method for machine
learning (ML). However, from a computational point of view they present a
challenge to existing eXplainable AI (xAI) methods. On the one hand,
measurements on quantum circuits introduce probabilistic errors which impact
the convergence of these methods. On the other hand, the phase space of a
quantum circuit expands exponentially with the number of qubits, complicating
efforts to execute xAI methods in polynomial time. In this paper we will
discuss the performance of established xAI methods, such as Baseline SHAP and
Integrated Gradients. Using the internal mechanics of PQCs we study ways to
speed up their computation.
Related papers
- Quantum Compiling with Reinforcement Learning on a Superconducting Processor [55.135709564322624]
We develop a reinforcement learning-based quantum compiler for a superconducting processor.
We demonstrate its capability of discovering novel and hardware-amenable circuits with short lengths.
Our study exemplifies the codesign of the software with hardware for efficient quantum compilation.
arXiv Detail & Related papers (2024-06-18T01:49:48Z) - Quantum Circuit Learning on NISQ Hardware [0.0]
Current quantum computers are small and error-prone systems.
Fault-tolerant quantum computers are not expected to be available in the near future.
We show that exemplary QCL circuits with up to three qubits are executable on the IBM quantum computer.
arXiv Detail & Related papers (2024-05-03T13:00:32Z) - Quantum Subroutine for Variance Estimation: Algorithmic Design and Applications [80.04533958880862]
Quantum computing sets the foundation for new ways of designing algorithms.
New challenges arise concerning which field quantum speedup can be achieved.
Looking for the design of quantum subroutines that are more efficient than their classical counterpart poses solid pillars to new powerful quantum algorithms.
arXiv Detail & Related papers (2024-02-26T09:32:07Z) - Quantum Simulation of Dissipative Energy Transfer via Noisy Quantum
Computer [0.40964539027092917]
We propose a practical approach to simulate the dynamics of an open quantum system on a noisy computer.
Our method leverages gate noises on the IBM-Q real device, enabling us to perform calculations using only two qubits.
In the last, to deal with the increasing depth of quantum circuits when doing Trotter expansion, we introduced the transfer tensor method(TTM) to extend our short-term dynamics simulation.
arXiv Detail & Related papers (2023-12-03T13:56:41Z) - An Algebraic Quantum Circuit Compression Algorithm for Hamiltonian
Simulation [55.41644538483948]
Current generation noisy intermediate-scale quantum (NISQ) computers are severely limited in chip size and error rates.
We derive localized circuit transformations to efficiently compress quantum circuits for simulation of certain spin Hamiltonians known as free fermions.
The proposed numerical circuit compression algorithm behaves backward stable and scales cubically in the number of spins enabling circuit synthesis beyond $mathcalO(103)$ spins.
arXiv Detail & Related papers (2021-08-06T19:38:03Z) - Adiabatic Quantum Graph Matching with Permutation Matrix Constraints [75.88678895180189]
Matching problems on 3D shapes and images are frequently formulated as quadratic assignment problems (QAPs) with permutation matrix constraints, which are NP-hard.
We propose several reformulations of QAPs as unconstrained problems suitable for efficient execution on quantum hardware.
The proposed algorithm has the potential to scale to higher dimensions on future quantum computing architectures.
arXiv Detail & Related papers (2021-07-08T17:59:55Z) - Variational quantum algorithm based on the minimum potential energy for
solving the Poisson equation [7.620967781722716]
We present a variational quantum algorithm for solving the Poisson equation.
The proposed method defines the total potential energy of the Poisson equation as a Hamiltonian.
Because the number of terms is independent of the size of the problem, this method requires relatively few quantum measurements.
arXiv Detail & Related papers (2021-06-17T09:01:53Z) - Towards a NISQ Algorithm to Simulate Hermitian Matrix Exponentiation [0.0]
A practical fault-tolerant quantum computer is worth looking forward to as it provides applications that outperform their known classical counterparts.
It would take decades to make it happen, exploiting the power of noisy intermediate-scale quantum(NISQ) devices, which already exist, is becoming one of current goals.
In this article, a method is reported as simulating a hermitian matrix exponentiation using parametrized quantum circuit.
arXiv Detail & Related papers (2021-05-28T06:37:12Z) - Preparation of excited states for nuclear dynamics on a quantum computer [117.44028458220427]
We study two different methods to prepare excited states on a quantum computer.
We benchmark these techniques on emulated and real quantum devices.
These findings show that quantum techniques designed to achieve good scaling on fault tolerant devices might also provide practical benefits on devices with limited connectivity and gate fidelity.
arXiv Detail & Related papers (2020-09-28T17:21:25Z) - ACSS-q: Algorithmic complexity for short strings via quantum accelerated
approach [1.4873907857806357]
We present a quantum circuit for estimating algorithmic complexity using the coding theorem method.
As a use-case, an application framework for protein-protein interaction based on algorithmic complexity is proposed.
arXiv Detail & Related papers (2020-09-18T14:41:41Z) - Quantum Geometric Machine Learning for Quantum Circuits and Control [78.50747042819503]
We review and extend the application of deep learning to quantum geometric control problems.
We demonstrate enhancements in time-optimal control in the context of quantum circuit synthesis problems.
Our results are of interest to researchers in quantum control and quantum information theory seeking to combine machine learning and geometric techniques for time-optimal control problems.
arXiv Detail & Related papers (2020-06-19T19:12:14Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.