Constructive Lower Bounds on Model Complexity of Shallow Perceptron Networks
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985807%3A_____%2F18%3A00474092" target="_blank" >RIV/67985807:_____/18:00474092 - isvavai.cz</a>
Result on the web
<a href="http://dx.doi.org/10.1007/s00521-017-2965-0" target="_blank" >http://dx.doi.org/10.1007/s00521-017-2965-0</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/s00521-017-2965-0" target="_blank" >10.1007/s00521-017-2965-0</a>
Alternative languages
Result language
angličtina
Original language name
Constructive Lower Bounds on Model Complexity of Shallow Perceptron Networks
Original language description
Limitations of shallow (one-hidden-layer) perceptron networks are investigated with respect to computing multivariable functions on finite domains. Lower bounds are derived on growth of the number of network units or sizes of output weights in terms of variations of functions to be computed. A concrete construction is presented with a class of functions which cannot be computed by signum or Heaviside perceptron networks with considerably smaller numbers of units and smaller output weights than the sizes of the function’s domains. A subclass of these functions is described whose elements can be computed by two-hidden-layer perceptron networks with the number of units depending on logarithm of the size of the domain linearly.
Czech name
—
Czech description
—
Classification
Type
J<sub>imp</sub> - Article in a specialist periodical, which is included in the Web of Science database
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
<a href="/en/project/GA15-18108S" target="_blank" >GA15-18108S: Model complexity of neural, radial, and kernel networks</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2018
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Name of the periodical
Neural Computing & Applications
ISSN
0941-0643
e-ISSN
—
Volume of the periodical
29
Issue of the periodical within the volume
7
Country of publishing house
US - UNITED STATES
Number of pages
11
Pages from-to
305-315
UT code for WoS article
000427799400002
EID of the result in the Scopus database
2-s2.0-85018255699