Limitations of Shallow Networks Representing Finite Mappings

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985807%3A_____%2F19%3A00485613" target="_blank" >RIV/67985807:_____/19:00485613 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1007/s00521-018-3680-1" target="_blank" >http://dx.doi.org/10.1007/s00521-018-3680-1</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/s00521-018-3680-1" target="_blank" >10.1007/s00521-018-3680-1</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Limitations of Shallow Networks Representing Finite Mappings

Popis výsledku v původním jazyce

Limitations of capabilities of shallow networks to efficiently compute real-valued functions on finite domains are investigated. Efficiency is studied in terms of network sparsity and its approximate measures. It is shown that when a dictionary of computational units is not sufficiently large, computation of almost any uniformly randomly chosen function either represents a well-conditioned task performed by a large network or an ill-conditioned task performed by a network of a moderate size. The probabilistic results are complemented by a concrete example of a class of functions which cannot be efficiently computed by shallow perceptron networks. The class is constructed using pseudo-noise sequences which have many features of random sequences but can be generated using special polynomials. Connections to the No Free Lunch Theorem and the central paradox of coding theory are discussed.

Název v anglickém jazyce

Limitations of Shallow Networks Representing Finite Mappings

Popis výsledku anglicky

Limitations of capabilities of shallow networks to efficiently compute real-valued functions on finite domains are investigated. Efficiency is studied in terms of network sparsity and its approximate measures. It is shown that when a dictionary of computational units is not sufficiently large, computation of almost any uniformly randomly chosen function either represents a well-conditioned task performed by a large network or an ill-conditioned task performed by a network of a moderate size. The probabilistic results are complemented by a concrete example of a class of functions which cannot be efficiently computed by shallow perceptron networks. The class is constructed using pseudo-noise sequences which have many features of random sequences but can be generated using special polynomials. Connections to the No Free Lunch Theorem and the central paradox of coding theory are discussed.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2019

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Neural Computing & Applications

ISSN

0941-0643

e-ISSN

—

Svazek periodika

31

Číslo periodika v rámci svazku

6

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

10

Strana od-do

1783-1792

Kód UT WoS článku

000470746700008

EID výsledku v databázi Scopus

2-s2.0-85052492938