Learning Capability of a Simple Neural Network
Abstract
We demonstrate that a neural network composed of only three nodes and three connections arranged in a 2-inputs, 1-middle, 1-output architecture is able to perform differentiation of univariate functions (Đ). Using a proposed empirical technique, we assess the network’s generalization capability by approximating a functional form for the growth function ΔF(N). We calculated the probability of error to be ≈10^-7 allowing us to justify the effectiveness of the simplistic approach in modeling a non-trivial task such as Đ.
Published
2012-07-03
Issue
Section
Articles
Keywords
architecture; differentiation; generalization; growth function
Submission of a manuscript implies: that the work described has not been published before (except in the form of an abstract or as part of a published lecture, review, or thesis); that it is not under consideration for publication elsewhere; that its publication has been approved by all co-authors, if any, as well as by the responsible authorities at the institute where the work has been carried out; that, if and when the manuscript is accepted for publication, the authors agree to the automatic transfer of the copyright to the publisher; that the manuscript will not be published elsewhere in any language without the consent of the copyright holders; that written permission of the copyright holder is obtained by the authors for material used from other copyrighted sources; and that any costs associated with obtaining this permission are the authors’ responsibility.