Enforcing exact permutation and rotational symmetries in the application of quantum neural networks on point cloud datasets
Open Access
- 10 October 2024
- journal article
- research article
- Published by American Physical Society (APS) in Physical Review Research
- Vol. 6 (4)
Abstract
Recent developments in the field of quantum machine learning have promoted the idea of incorporating physical symmetries in the structure of quantum circuits. A crucial milestone in this area is the realization of S n -permutation equivariant quantum neural networks (QNNs) that are equivariant under permutations of input objects. In this paper, we focus on encoding the rotational symmetry of point cloud datasets into the QNN. The key insight of the approach is that all rotationally invariant functions with vector inputs are equivalent to a function with inputs of vector inner products. We provide a structure of the QNN that is exactly invariant to both rotations and permutations, with its efficacy demonstrated numerically in the problems of two-dimensional image classifications and identifying high-energy particle decays, produced by proton-proton collisions, with the SO ( 1 , 3 ) Lorentz symmetry. Published by the American Physical Society 2024Keywords
All Related Versions
Funding Information
- Japan Science and Technology Agency (JPMJPF2221)
This publication has 39 references indexed in Scilit:
- Permutation invariant encodings for quantum machine learning with point cloud dataQuantum Machine Intelligence, 2024
- Quantum convolutional neural network for classical data classificationQuantum Machine Intelligence, 2022
- Recent advances for quantum classifiersScience China Physics, Mechanics & Astronomy, 2021
- Cost function dependent barren plateaus in shallow parametrized quantum circuitsNature Communications, 2021
- Quantum machine learning for particle physics using a variational quantum classifierJournal of High Energy Physics, 2021
- Event Classification with Quantum Machine Learning in High-Energy PhysicsComputing and Software for Big Science, 2021
- Barren plateaus in quantum neural network training landscapesNature Communications, 2018
- Solving a Higgs optimization problem with quantum annealing for machine learningNature, 2017
- Quantum machine learningNature, 2017
- Direct search algorithms for optimization calculationsActa Numerica, 1998