English

Markovian Quantum Neuroevolution for Machine Learning

Quantum Physics 2021-11-03 v2 Disordered Systems and Neural Networks

Abstract

Neuroevolution, a field that draws inspiration from the evolution of brains in nature, harnesses evolutionary algorithms to construct artificial neural networks. It bears a number of intriguing capabilities that are typically inaccessible to gradient-based approaches, including optimizing neural-network architectures, hyperparameters, and even learning the training rules. In this paper, we introduce a quantum neuroevolution algorithm that autonomously finds near-optimal quantum neural networks for different machine-learning tasks. In particular, we establish a one-to-one mapping between quantum circuits and directed graphs, and reduce the problem of finding the appropriate gate sequences to a task of searching suitable paths in the corresponding graph as a Markovian process. We benchmark the effectiveness of the introduced algorithm through concrete examples including classifications of real-life images and symmetry-protected topological states. Our results showcase the vast potential of neuroevolution algorithms in quantum architecture search, which would boost the exploration towards quantum-learning advantage with noisy intermediate-scale quantum devices.

Keywords

Cite

@article{arxiv.2012.15131,
  title  = {Markovian Quantum Neuroevolution for Machine Learning},
  author = {Zhide Lu and Pei-Xin Shen and Dong-Ling Deng},
  journal= {arXiv preprint arXiv:2012.15131},
  year   = {2021}
}

Comments

7 pages (main text) + 5.5 pages (supplementary materials), 14 figures

R2 v1 2026-06-23T21:35:44.405Z