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

246 910 (0,304s)

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

Approximating Multivariable Functions by Feedforward Neural Nets

Theoretical results on approximation of multivariable functions by feedforward neural networks are surveyed. Some proofs of universal approximation capabilities of rates of decrease of approximation errors with increasing <...

IN - Informatika

  • 2013
  • C
  • Link
Result

Accuracy of surrogate solutions of integral equations by feedforward networks

Surrogate solutions of Fredholm integral equations by feedforward neural networks are investigated theoretically. Convergence of surrogate solutions computable by networks with increasing numbers of computational u...

IN - Informatika

  • 2014
  • C
  • Link
Result

Implementation of Kolmogorov Learning Algorithm for Feedforward Neural Networks.

We present a learning algorithm for feedforward neural networks that is based on Kolmogorov theorem concerning composition of n-dimensional countinuous function from one-dimensional continuous functions. A through analysis ...

BA - Obecná matematika

  • 2001
  • D
Result

The Application of Structured Feedforward Neural Networks to the Modelling of the Daily Series of Currency in Circulation

The paper introduces feedforward structured neural network model and discusses its applicability to the forecasting of the currency in circulation. The forecasting performance of the new neural network...

BA - Obecná matematika

  • 2005
  • D
Result

Surrogate solutions of Fredholm equations by feedforward networks

Surrogate solutions of Fredholm integral equations by feedforward neural networks are investigated theoretically. Convergence of surrogate solutions computable by networks with increasing numbers of computational u...

IN - Informatika

  • 2012
  • D
Result

NONLINEAR MODELING OF LABORATORY MODEL AMIRA DR300 BY FEEDFORWARD NEURAL NETWORK

Purpose of this paper is to design a nonlinear feedforward neural network model of a laboratory model AMIRA DR300 (made by AMIRA, Duisburg, Germany). This device consists position sensor. The first engine ...

BC - Teorie a systémy řízení

  • 2011
  • D
Result

Universality and Complexity of Approximation of Multivariable Functions by Feedforward Networks.

A theoretical framework for investigation of approximation capabilities of feed-forward networks is presented in the context of nonlinear approximation theory. Some recent results of universal approximation property and estimates of netw...

BA - Obecná matematika

  • 2002
  • D
Result

Kolmogorov Learning for Feedforward Networks.

We present a learning algorithm for feedforward neural networks that is based on Kolmogorov theorem concerning composition of n-dimensional continuous function from one-dimensional continuous functions. A thorough analysis ...

BA - Obecná matematika

  • 2001
  • D
Result

An orthogonal neural network for nonlinear function modelling

The paper is dealing with the multilayer feedforward network...

JC - Počítačový hardware a software

  • 2007
  • Jx
  • 1 - 10 out of 246 910