

Author: Engel A. Malzahn D. Kanter I.
Publisher: Taylor & Francis Ltd
ISSN: 1463-6417
Source: Philosophical Magazine B, Vol.77, Iss.5, 1998-05, pp. : 1507-1513
Disclaimer: Any content in publications that violate the sovereignty, the constitution or regulations of the PRC is not accepted or approved by CNPIEC.
Abstract
Feedforward multilayer neural networks implementing random input-output develop characteristic correlations between the activity of their hidden which are important for the understanding of their storage and performance. It is shown how these correlations can be within the replica-symmetric approximation. Replacing the network by an ensemble of perceptrons displaying the same the relative influence of these correlations on the storage capacity be studied.
Related content


Statistical Properties of Strongly Correlated Quantum Liquids
Foundations of Physics, Vol. 40, Iss. 9-10, 2010-10 ,pp. :


Learning and generalization in higher-order perceptrons
By Yoon Hyoungsoo Oh Jong-Hoon
Philosophical Magazine B, Vol. 77, Iss. 5, 1998-05 ,pp. :




Optical properties of AlN thin films correlated with sputtering conditions
By Gadenne M. Plon J. Gadenne P.
Thin Solid Films, Vol. 333, Iss. 1, 1998-11 ,pp. :