Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.21135 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909709945012224 |
|---|---|
| author | Abanov, Alexander G. Candelori, Luca Steinacker, Harold C. Wells, Martin T. Busemeyer, Jerome R. Hogan, Cameron J. Kirakosyan, Vahagn Marzari, Nicola Pinnamaneni, Sunil Villani, Dario Xu, Mengjia Musaelian, Kharen |
| author_facet | Abanov, Alexander G. Candelori, Luca Steinacker, Harold C. Wells, Martin T. Busemeyer, Jerome R. Hogan, Cameron J. Kirakosyan, Vahagn Marzari, Nicola Pinnamaneni, Sunil Villani, Dario Xu, Mengjia Musaelian, Kharen |
| contents | We demonstrate how Quantum Cognition Machine Learning (QCML) encodes data as quantum geometry. In QCML, features of the data are represented by learned Hermitian matrices, and data points are mapped to states in Hilbert space. The quantum geometry description endows the dataset with rich geometric and topological structure - including intrinsic dimension, quantum metric, and Berry curvature - derived directly from the data. QCML captures global properties of data, while avoiding the curse of dimensionality inherent in local methods. We illustrate this on a number of synthetic and real-world examples. Quantum geometric representation of QCML could advance our understanding of cognitive phenomena within the framework of quantum cognition. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_21135 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Quantum Geometry of Data Abanov, Alexander G. Candelori, Luca Steinacker, Harold C. Wells, Martin T. Busemeyer, Jerome R. Hogan, Cameron J. Kirakosyan, Vahagn Marzari, Nicola Pinnamaneni, Sunil Villani, Dario Xu, Mengjia Musaelian, Kharen Machine Learning Quantum Physics We demonstrate how Quantum Cognition Machine Learning (QCML) encodes data as quantum geometry. In QCML, features of the data are represented by learned Hermitian matrices, and data points are mapped to states in Hilbert space. The quantum geometry description endows the dataset with rich geometric and topological structure - including intrinsic dimension, quantum metric, and Berry curvature - derived directly from the data. QCML captures global properties of data, while avoiding the curse of dimensionality inherent in local methods. We illustrate this on a number of synthetic and real-world examples. Quantum geometric representation of QCML could advance our understanding of cognitive phenomena within the framework of quantum cognition. |
| title | Quantum Geometry of Data |
| topic | Machine Learning Quantum Physics |
| url | https://arxiv.org/abs/2507.21135 |