Model Complexities of Shallow Networks Representing Highly Varying Functions
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985807%3A_____%2F16%3A00446410" target="_blank" >RIV/67985807:_____/16:00446410 - isvavai.cz</a>
Result on the web
<a href="http://dx.doi.org/10.1016/j.neucom.2015.07.014" target="_blank" >http://dx.doi.org/10.1016/j.neucom.2015.07.014</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1016/j.neucom.2015.07.014" target="_blank" >10.1016/j.neucom.2015.07.014</a>
Alternative languages
Result language
angličtina
Original language name
Model Complexities of Shallow Networks Representing Highly Varying Functions
Original language description
Model complexities of shallow (i.e., one-hidden-layer) networks representing highly varying multivariable {-1,1}{-1,1}-valued functions are studied in terms of variational norms tailored to dictionaries of network units. It is shown that bounds on thesenorms define classes of functions computable by networks with constrained numbers of hidden units and sizes of output weights. Estimates of probabilistic distributions of values of variational norms with respect to typical computational units, such as perceptrons and Gaussian kernel units, are derived via geometric characterization of variational norms combined with the probabilistic Chernoff Bound. It is shown that almost any randomly chosen {-1,1}{-1,1}-valued function on a sufficiently large d-dimensional domain has variation with respect to perceptrons depending on d exponentially.
Czech name
—
Czech description
—
Classification
Type
J<sub>x</sub> - Unclassified - Peer-reviewed scientific article (Jimp, Jsc and Jost)
CEP classification
IN - Informatics
OECD FORD branch
—
Result continuities
Project
<a href="/en/project/LD13002" target="_blank" >LD13002: Modeling of complex systems for softcomputing methods</a><br>
Continuities
I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace
Others
Publication year
2016
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Name of the periodical
Neurocomputing
ISSN
0925-2312
e-ISSN
—
Volume of the periodical
171
Issue of the periodical within the volume
1 January
Country of publishing house
NL - THE KINGDOM OF THE NETHERLANDS
Number of pages
7
Pages from-to
598-604
UT code for WoS article
000364883900062
EID of the result in the Scopus database
2-s2.0-84947029082