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

41 198 (0,163s)

Result

Hybrid Convolutional Neural Networks

The article proposes a new variant of convolutional neural networks - hybrid convolutional neural networks. This model of the network uses the 'winner-takes-all' principle and RBF-neurons in all itslayers....

BD - Teorie informace

  • 2008
  • D
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...

IN - Informatika

  • 2016
  • D
  • Link
Result

Convolutive Bottleneck Network Features for LVCSR

Workshop Article about novel features for tandem LVCSR system, which are based on Convolutive Bottleneck Network. It extends the previous work on Universal Context network by using linear bottleneck and expansion to Con...

JC - Počítačový hardware a software

  • 2011
  • D
Result

Deep Convolutional Neural Network for Fire Detection

Detection of smoke and fire using deep convolutional neural network to process video signals from camera.

Communication engineering and systems

  • 2020
  • D
  • Link
Result

The Use of Convolutional Neural Networks in Biomedical Data Processing

In this work, we study the use of convolutional neural networks for biomedical signal processing. Convolutional neural networks show promising results for classifying images when compared to traditional multilayer ...

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

  • 2017
  • D
  • Link
Result

Compression Artifacts Removal Using Convolutional Neural Networks

This paper shows that it is possible to train large and deep convolutional neural networks (CNN) for JPEG compression artifacts reduction....

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

  • 2016
  • JSC
  • Link
Result

Time Series Convolution Kernel Estimation

Main topics of the document: convolution kernel; time series; estimation; visualization; neural network...

Statistics and probability

  • 2018
  • D
  • Link
Result

Convolutional Neural Networks with Interpretable Kernels

We are focused on the theoretical background of convolutional neural networks. In particular, we examine the problem whether semantic meaning can be assigned to convolutional kernels in the first layers and how this fact ca...

Applied mathematics

  • 2019
  • D
  • Link
Result

Multivariable Approximation by Convolutional Kernel Networks

of convolutional kernels determine whether sets of input-output functions of networksComputational units induced by convolutional kernels together with biologically in neurocomputing. Radial convolutional kernels ...

IN - Informatika

  • 2016
  • D
  • Link
Result

Asynchronous Evolution of Convolutional Networks

Due to many successful practical applications, deep neural networks and convolutional networks have become the state-of-art machine learning methods recently. The choice of network architecture for the task at hand...

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

  • 2018
  • D
  • Link
  • 1 - 10 out of 41 198