Representations of highly-varying functions by perceptron networks

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985807%3A_____%2F13%3A00396820" target="_blank" >RIV/67985807:_____/13:00396820 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Representations of highly-varying functions by perceptron networks
Original language description
Tractability of representations of multivariable functions by perceptron networks is investigated. There are described classes of functions which cannot be tractably represented by Heaviside perceptron networks in the sense that all their representationsby such networks require numbers of units or sizes of output weights depending exponentially on the number of variables d. It is shown that the concept of variational norm from approximation theory can play a role of a measure of such tractability. Existence of large sets of Boolean functions with variations depending on d exponentially is proven. The results are illustrated by an example of a class of Boolean functions defined in terms of their communication matrices.
Czech name
—
Czech description
—

Project
<a href="/en/project/GAP202%2F11%2F1368" target="_blank" >GAP202/11/1368: Learning of functional relationships from high-dimensional data</a><br>
Continuities
I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year
2013
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
ITAT 2013: Information Technologies - Applications and Theory Workshops, Posters, and Tutorials
ISBN
978-1-4909-5208-6
ISSN
—
e-ISSN
—
Number of pages
4
Pages from-to
73-76
Publisher name
CreateSpace Independent Publishing Platform
Place of publication
North Charleston
Event location
Donovaly
Event date
Sep 11, 2013
Type of event by nationality
EUR - Evropská akce
UT code for WoS article
—

Similar results(10)