All

What are you looking for?

All
Projects
Results
Organizations

Quick search

  • Projects supported by TA ČR
  • Excellent projects
  • Projects with the highest public support
  • Current projects

Smart search

  • That is how I find a specific +word
  • That is how I leave the -word out of the results
  • “That is how I can find the whole phrase”

Filters

25 (0,097s)

Result

Radial Fuzzy Systems

The class of radial fuzzy systems is introduced. The fuzzy systems in this class use radial functions to implement membership functions of fuzzy sets and exhibit a shape preservation property in antecedents of their rules. The property is called the ...

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

  • 2017
  • Jimp
  • Link
Result

Model Complexities of Shallow Networks Representing Highly Varying Functions

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 th...

IN - Informatika

  • 2016
  • Jx
  • Link
Result

Kernel Networks for Function Approximation

Capabilities of radial convolution kernel networks to approximate multivariate functions are investigated. A necessary condition for universal approximation property of convolution kernel networks is given. Kernels that satisfy the condition in arbit...

IN - Informatika

  • 2016
  • D
  • Link
Result

Data Mining Process Optimization in Computational Multi-agent Systems

In this paper, we present an agent-based solution of metalearning problem which focuses on optimization of data mining processes. We exploit the framework of computational multi-agent systems in which various meta-learning problems have been already ...

IN - Informatika

  • 2015
  • D
  • Link
Result

Limitations of One-Hidden-Layer Perceptron Networks

Limitations of one-hidden-layer perceptron networks to represent efficiently finite mappings is investigated. It is shown that almost any uniformly randomly chosen mapping on a sufficiently large finite domain cannot be tractably represented by a one...

IN - Informatika

  • 2015
  • D
Result

Model Complexity of Neural Networks - a Seeming Paradox

The paper investigates limitations of one-hidden-layer artificial neural networks for solving high-dimensional tasks.

IN - Informatika

  • 2015
  • D
  • Link
Result

RBF Neural Networks and Radial Fuzzy Systems

RBF neural networks are an efficient tool for acquisition and representation of functional relations reflected in empirical data. The interpretation of acquired knowledge is, however, generally difficult because the knowledge is encoded into values o...

IN - Informatika

  • 2015
  • D
  • Link
Result

Degree of Coverage of Radial Rule Bases

The paper discusses how a rule base covers its input space in radial fuzzy systems. We investigate the minimal degree of firing of rules in the rule base when moving across the input space. This minimal degree is called the degree of coverage (DOC) a...

IN - Informatika

  • 2015
  • D
  • Link
Result

Coherence and Convexity of Euclidean Radial Implicative Fuzzy Systems

The chapter discuss a necessary condition for coherence of radial implicative fuzzy systems. We present the general condition in an implicit form. The condition is based on the value of the minima of a certain function. We show that this function is ...

IN - Informatika

  • 2014
  • C
  • Link
Result

Representations of Highly-Varying Functions by One-Hidden-Layer Networks

Limitations of capabilities of one-hidden-layer networks are investigated. It is shown that for networks with Heaviside perceptrons as well as for networks with kernel units used in SVM, there exist large sets of d-variable functions which cannot be ...

IN - Informatika

  • 2014
  • D
  • Link
  • 1 - 10 out of 25