Výsledky vyhledávání - "Endo, Yasuhiro"

Report

Resource-efficient equivariant quantum convolutional neural networks

Autor: Chinzei, Koki, Tran, Quoc Hoan, Endo, Yasuhiro, Oshima, Hirotaka

Equivariant quantum neural networks (QNNs) are promising quantum machine learning models that exploit symmetries to provide potential quantum advantages. Despite theoretical developments in equivariant QNNs, their implementation on near-term quantum

Externí odkaz: http://arxiv.org/abs/2410.01252

Zobrazit plný text záznamu

Report

Quantum Curriculum Learning

Autor: Tran, Quoc Hoan, Endo, Yasuhiro, Oshima, Hirotaka

Quantum machine learning (QML) requires significant quantum resources to achieve quantum advantage. Research should prioritize both the efficient design of quantum architectures and the development of learning strategies to optimize resource usage. W

Externí odkaz: http://arxiv.org/abs/2407.02419

Zobrazit plný text záznamu

Report

Trade-off between Gradient Measurement Efficiency and Expressivity in Deep Quantum Neural Networks

Autor: Chinzei, Koki, Yamano, Shinichiro, Tran, Quoc Hoan, Endo, Yasuhiro, Oshima, Hirotaka

Quantum neural networks (QNNs) require an efficient training algorithm to achieve practical quantum advantages. A promising approach is the use of gradient-based optimization algorithms, where gradients are estimated through quantum measurements. How

Externí odkaz: http://arxiv.org/abs/2406.18316

Zobrazit plný text záznamu