Parametric t-Stochastic Neighbor Embedding With Quantum Neural Network. Kawase, Y., Mitarai, K., & Fujii, K. February, 2022. arXiv:2202.04238 [quant-ph]
Parametric t-Stochastic Neighbor Embedding With Quantum Neural Network [link]Paper  abstract   bibtex   
t-Stochastic Neighbor Embedding (t-SNE) is a non-parametric data visualization method in classical machine learning. It maps the data from the high-dimensional space into a low-dimensional space, especially a two-dimensional plane, while maintaining the relationship, or similarities, between the surrounding points. In t-SNE, the initial position of the low-dimensional data is randomly determined, and the visualization is achieved by moving the low-dimensional data to minimize a cost function. Its variant called parametric t-SNE uses neural networks for this mapping. In this paper, we propose to use quantum neural networks for parametric t-SNE to reflect the characteristics of high-dimensional quantum data on low-dimensional data. We use fidelity-based metrics instead of Euclidean distance in calculating high-dimensional data similarity. We visualize both classical (Iris dataset) and quantum (time-depending Hamiltonian dynamics) data for classification tasks. Since this method allows us to represent a quantum dataset in a higher dimensional Hilbert space by a quantum dataset in a lower dimension while keeping their similarity, the proposed method can also be used to compress quantum data for further quantum machine learning.
@misc{kawase_parametric_2022,
	title = {Parametric t-{Stochastic} {Neighbor} {Embedding} {With} {Quantum} {Neural} {Network}},
	url = {http://arxiv.org/abs/2202.04238},
	abstract = {t-Stochastic Neighbor Embedding (t-SNE) is a non-parametric data visualization method in classical machine learning. It maps the data from the high-dimensional space into a low-dimensional space, especially a two-dimensional plane, while maintaining the relationship, or similarities, between the surrounding points. In t-SNE, the initial position of the low-dimensional data is randomly determined, and the visualization is achieved by moving the low-dimensional data to minimize a cost function. Its variant called parametric t-SNE uses neural networks for this mapping. In this paper, we propose to use quantum neural networks for parametric t-SNE to reflect the characteristics of high-dimensional quantum data on low-dimensional data. We use fidelity-based metrics instead of Euclidean distance in calculating high-dimensional data similarity. We visualize both classical (Iris dataset) and quantum (time-depending Hamiltonian dynamics) data for classification tasks. Since this method allows us to represent a quantum dataset in a higher dimensional Hilbert space by a quantum dataset in a lower dimension while keeping their similarity, the proposed method can also be used to compress quantum data for further quantum machine learning.},
	language = {en},
	urldate = {2023-06-27},
	publisher = {arXiv},
	author = {Kawase, Yoshiaki and Mitarai, Kosuke and Fujii, Keisuke},
	month = feb,
	year = {2022},
	note = {arXiv:2202.04238 [quant-ph]},
	keywords = {Quantum Physics, Computer Science - Machine Learning},
	annote = {Comment: 9 pages, 7 figures},
	file = {Kawase et al. - 2022 - Parametric t-Stochastic Neighbor Embedding With Qu.pdf:/Users/georgehuang/Zotero/storage/QZA7B2B2/Kawase et al. - 2022 - Parametric t-Stochastic Neighbor Embedding With Qu.pdf:application/pdf},
}

Downloads: 0