Strong generalization in quantum neural networks

Article Computer Science, Artificial Intelligence

Towards quantum enhanced adversarial robustness in machine learning

Maxwell T. West et al.

Summary: Machine learning algorithms are powerful but vulnerable to adversarial attacks. Integrating quantum computing with machine learning can improve accuracy and provide better defense against such attacks.

NATURE MACHINE INTELLIGENCE (2023)

Add to Collection

Article Physics, Multidisciplinary

Quantum Version of the k-NN Classifier Based on a Quantum Sorting Algorithm

L. F. Quezada et al.

Summary: This work introduces a quantum sorting algorithm with adaptable memory and circuit depth requirements, and applies it to develop a new quantum version of the classical machine learning algorithm called k-nearest neighbors (k-NN). The efficiency and performance of this new quantum k-NN algorithm are compared to the classical k-NN and another quantum version proposed by Schuld et al. The results show that both quantum algorithms have similar efficiency and outperform the classical algorithm. Moreover, the proposed quantum k-NN algorithm performs better than the one proposed by Schuld et al. and is similar to the classical k-NN.

ANNALEN DER PHYSIK (2022)

Add to Collection

Article Multidisciplinary Sciences

Generalization in quantum machine learning from few training data

Matthias C. Caro et al.

Summary: This study provides a comprehensive investigation into the generalization performance of QML on a limited training data set. The results show the relationship between the generalization error of a quantum machine learning model and the number of trainable gates, as well as the potential applications of quantum convolutional neural networks and learning quantum error correcting codes or quantum dynamical simulation.

NATURE COMMUNICATIONS (2022)

Add to Collection

Article Multidisciplinary Sciences

Power of data in quantum machine learning

Hsin-Yuan Huang et al.

Summary: The study demonstrates that classical machine learning models, even if tailored for quantum problems, can compete with quantum models with the help of data. By introducing rigorous prediction error bounds, a methodology for assessing potential quantum advantage in learning tasks is developed.

NATURE COMMUNICATIONS (2021)

Add to Collection

Article Multidisciplinary Sciences

Cost function dependent barren plateaus in shallow parametrized quantum circuits

M. Cerezo et al.

Summary: In this study, the authors rigorously prove that defining cost functions with local observables can avoid the barren plateau problem, while defining them with global observables leads to exponentially vanishing gradients. The results indicate a connection between locality and trainability in variational quantum algorithms (VQAs).

NATURE COMMUNICATIONS (2021)

Add to Collection

Article Computer Science, Interdisciplinary Applications

The power of quantum neural networks

Amira Abbas et al.

Summary: This study investigates the advantage of near-term quantum computers for machine learning tasks by comparing the power and trainability of quantum machine learning models with classical neural networks. The effective dimension, a data-dependent measure based on Fisher information, is proposed to evaluate a model's ability to generalize on new data. Numerical demonstrations show that quantum neural networks outperform comparable feedforward networks in effective dimension and training speed, indicating an advantage for quantum machine learning validated on real quantum hardware.

NATURE COMPUTATIONAL SCIENCE (2021)

Add to Collection

Article Multidisciplinary Sciences