Approximation of Classifiers by Deep Perceptron Networks

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985807%3A_____%2F23%3A00572576" target="_blank" >RIV/67985807:_____/23:00572576 - isvavai.cz</a>
Result on the web
<a href="https://dx.doi.org/10.1016/j.neunet.2023.06.004" target="_blank" >https://dx.doi.org/10.1016/j.neunet.2023.06.004</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1016/j.neunet.2023.06.004" target="_blank" >10.1016/j.neunet.2023.06.004</a>

Result language
angličtina
Original language name
Approximation of Classifiers by Deep Perceptron Networks
Original language description
We employ properties of high-dimensional geometry to obtain some insights into capabilities of deep perceptron networks to classify large data sets. We derive conditions on network depths, types of activation functions, and numbers of parameters that imply that approximation errors behave almost deterministically. We illustrate general results by concrete cases of popular activation functions: Heaviside, ramp sigmoid, rectified linear, and rectified power. Our probabilistic bounds on approximation errors are derived using concentration of measure type inequalities (method of bounded differences) and concepts from statistical learning theory.
Czech name
—
Czech description
—

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)

Project
<a href="/en/project/GA22-02067S" target="_blank" >GA22-02067S: AppNeCo: Approximate Neurocomputing</a><br>
Continuities
I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year
2023
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Similar results(10)