Singular-Value-Decomposition Analysis of Associative Memory in a Neural Network
Authors:
- 15 February 2017
- journal article
- research article
- Published by Physical Society of Japan in Journal of the Physical Society of Japan
- Vol. 86 (2)
Abstract
We evaluate performance of associative memory in a neural network by based on the singular value decomposition (SVD) of image data stored in the network. We consider the situation in which the original image and its highly coarse-grained one by SVD are stored in the network and the intermediate one is taken as an input. We find that the performance is characterized by the snapshot-entropy scaling inherent in the SVD: the network retrieves the original image when the entropy of the input image is larger than the critical value determined from the scaling. The result indicates efficiency of the SVD as a criterion of the performance and also indicates universality of the scaling for realistic problems beyond theoretical physics.Keywords
All Related Versions
This publication has 29 references indexed in Scilit:
- Theory of Finite-Entanglement Scaling at One-Dimensional Quantum Critical PointsPhysical Review Letters, 2009
- Algorithms for entanglement renormalizationPhysical Review B, 2009
- Scaling of entanglement support for matrix product statesPhysical Review B, 2008
- Entanglement RenormalizationPhysical Review Letters, 2007
- Entanglement entropy and quantum field theoryJournal of Statistical Mechanics: Theory and Experiment, 2004
- Density-matrix renormalization group for a gapless system of free fermionsPhysical Review B, 1999
- The large $N$ limit of superconformal field theories and supergravityAdvances in Theoretical and Mathematical Physics, 1998
- Geometric and renormalized entropy in conformal field theoryNuclear Physics B, 1994
- Density-matrix algorithms for quantum renormalization groupsPhysical Review B, 1993
- Density matrix formulation for quantum renormalization groupsPhysical Review Letters, 1992