Vše

Co hledáte?

Vše
Projekty
Výsledky výzkumu
Subjekty

Rychlé hledání

  • Projekty podpořené TA ČR
  • Významné projekty
  • Projekty s nejvyšší státní podporou
  • Aktuálně běžící projekty

Chytré vyhledávání

  • Takto najdu konkrétní +slovo
  • Takto z výsledků -slovo zcela vynechám
  • “Takto můžu najít celou frázi”

Filtry

50 958 (0,121s)

Výsledek výzkumu

Regression Neural Networks with a Highly Robust Loss Function

far, only a few robust alternatives for training common forms of neural networks of situations. Robust neural networks are even able to outperform the prediction abilityArtificial neural...

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

  • 2020
  • D
  • Odkaz
Výsledek výzkumu

Robust Multilayer Perceptrons: Robust Loss Functions and Their Derivatives

available robust alternatives for training common form of neural networks. In this work consider robust neural networks based on the robust loss function of the least trimmed in implemen...

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

  • 2020
  • D
  • Odkaz
Výsledek výzkumu

Robust filtering of time series

Main topics of the document: robust filtering; technical analysis; artificial neural networks; forecasting in time series......

BB - Aplikovaná statistika, operační výzkum

  • 2011
  • D
Výsledek výzkumu

On Robust Training of Regression Neural Networks

robust versions of common types of neural networks, namely multilayer perceptrons and radial basis function networks, are proposed here based on nonlinear regression variables. Neural networks, c...

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

  • 2020
  • D
  • Odkaz
Výsledek výzkumu

On Robust Training of Regression Neural Networks

robust versions of common types of neural networks, namely multilayer perceptrons and radial basis function networks, are proposed here based on nonlinear regression variables. Neural networks, c...

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

  • 2021
  • O
Výsledek výzkumu

On the Bayesian Interpretation of Robust Regression Neural Networks

neural networks with available prior information, i.e. a likelihood-based perspective of training neural networks. Attention is also paid to very recently proposed regularized versions of robust neura...

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

  • 2024
  • D
  • Odkaz
Výsledek výzkumu

Deep Networks with RBF Layers to Prevent Adversarial Examples

We propose a simple way to increase the robustness of deep neural network models to adversarial examples. The new architecture obtained by stacking deep neural network and RBF network is proposed....

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

  • 2018
  • D
  • Odkaz
Výsledek výzkumu

Robust Optimal-Size Implementation of Finite State Automata with Synfire Ring-Based Neural Networks

an optimal-size implementation of finite state automata with neural networks composed neural network partly composed of synfire rings capable of simulating it. The synfire computation. The robustness of t...

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

  • 2019
  • D
  • Odkaz
Výsledek výzkumu

Robust interquantile training of neural networks

Standard types of artificial neural networks commonly used for the regression. The software performs robust training of multilayer perceptrons or radial basis function networks by means of quantiles, which are them...

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

  • 2019
  • R
  • Odkaz
Výsledek výzkumu

Robust Neural Network-Based Estimation of Articulatory Features for Czech

The article describes a neural network-based articulatory feature (AF inventory is defined, and then the estimation based on the MLP neural networks is done is proposed with the purpose to obtain a robust ...

JA - Elektronika a optoelektronika, elektrotechnika

  • 2014
  • Jx
  • Odkaz
  • 1 - 10 z 50 958