A Hebb-type learning equation on the quantum information space - a clue to a fast principal component analyzer

zbMATH Open1206.68264arXiv0912.3328MaRDI QIDQ3067702FDOQ3067702

Authors: Hiromi Yuya, Yoshio Uwano 

Publication date: 21 January 2011

Abstract: The averaged learning equation (ALEH) applicable to the principal component analyzer is studied from both quantum information geometry and dynamical system viewpoints. On the quantum information space (QIS), the space of regular density matrices endowed with the quantum SLD-Fisher metric, a gradient system is given as an extension of the ALEH; on the submanifold, consisting of the diagonal matrices, of the QIS, the gradient flow coincides with the ALEH up to a local diffeomorphism.

Full work available at URL: https://arxiv.org/abs/0912.3328

Recommendations

• Stability and Convergence of Principal Component Learning Algorithms
• The dynamics of on-line principal component analysis
• Quantum learning algorithms for quantum measurements
• On principal subspace analysis
• An improved quantum principal component analysis algorithm based on the quantum singular threshold method

zbMATH Keywords

multivariate analysisgradient systemslearning equationquantum information space

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Quantum computation (81P68) Differential geometric methods (tensors, connections, symplectic, Poisson, contact, Riemannian, nonholonomic, etc.) for problems in mechanics (70G45) Differential geometric methods, including holonomy, Berry and Hannay phases, Aharonov-Bohm effect, etc. in quantum theory (81Q70)

This page was built for publication: A Hebb-type learning equation on the quantum information space - a clue to a fast principal component analyzer

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3067702)