Author： Yoon Hyoungsoo Oh Jong-Hoon
Publisher： Taylor & Francis Ltd
ISSN： 1463-6417
Source： Philosophical Magazine B, Vol.77, Iss.5, 1998-05, pp. : 1557-1563
Disclaimer: Any content in publications that violate the sovereignty, the constitution or regulations of the PRC is not accepted or approved by CNPIEC.
Abstract
We study learning from examples in higher-order perceptrons, which can realize polynomially separable rules. We first calculate the storage capacity of random binary patterns. It is found that the storage capacity is a monotonically increasing function of the relative weight parameter of the highest-order monomial term. We also analyse the generalization ability of higher-order perceptrons when they are trained by examples drawn from a realizable rule. Unlike their first-order counterparts, high-order perceptrons are found to exhibit stepwise learning as a function of the number of training examples.
Related content
Access to resources
Recommend
On higher-order quantum stress
Acta Mechanica, Vol. 225, Iss. 4-5, 2014-04 ,pp. :
Higher-order conditions for strict efficiency
By Ginchev Ivan
Optimization, Vol. 60, Iss. 3, 2011-01 ,pp. :
On the Theory of Higher-Order Painlevé Equations
By Gromak V. I. Zenchenko A. S.
Differential Equations, Vol. 40, Iss. 5, 2004-05 ,pp. :