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

43 144 (0,094s)

Result

Towards CNN-based food detection and recognition in refrigerators

This report describes the first steps towards a Convolutional Neural Network (CNN) based food detection and recognition system for refrigerators....

JD - Využití počítačů, robotika a její aplikace

  • 2016
  • Vsouhrn
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

Hierarchical Discriminative Model for Spoken Language Understanding Based on Convolutional Neural Network

artificial neural networks. It is based on the existing work focused on the text classification using convolutional neural networks (CNNs). The presented method generalizes the convolutional<...

Automation and control systems

  • 2015
  • D
  • Link
Result

Classification of Traffic Signs by Convolutional Neural Networks

The paper presented here describes traffic signs classification method based on a convolutional neural network (CNN). The CNN was trained and tested on the public database of German traffic signs with 43 m...

Robotics and automatic control

  • 2018
  • D
  • Link
Result

Optimizing Convolutional Neural Networks for Embedded Systems By Means of Neuroevolution

Automated design methods for convolutional neural networks (CNNs) have recently been developed in order to increase the design productivity. We propose a neuroevolution method capable of evolving and optimizing

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

  • 2019
  • D
  • Link
Result

TypeCNN: CNN Development Framework With Flexible Data Types

and convolutional neural networks (CNN) has led to an enormous interest in efficient implementations of neural networks in embedded devices and hardware. We present a new software framework for t...

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

  • 2019
  • D
  • Link
Result

Classification of Czech sign language alphabet letters using cnn – preliminary study

Abstract: The paper deals with the classification of Czech sign language single hand alphabet letters from static images using convolutional neural network (CNN). Proposed CNN architecture exhibits about ...

Robotics and automatic control

  • 2020
  • D
  • Link
Result

Application of Convolutional Neural Networks in Neutrino Physics

The application of deep learning methods has in past years enabled new discoveries in many fields of study and neutrino physics is no exception. As a deep learning algorithm, convolutional neural networks (CNNs) sh...

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

  • 2019
  • D
  • Link
Result

Energy Complexity Model for Convolutional Neural Networks

The energy efficiency of hardware implementations of convolutional neural networks (CNNs) is critical to their widespread deployment in low-power mobile devices of CNNs onto diverse hardware accelerators. ...

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

  • 2023
  • D
  • Link
Result

Segmentation of Actin-Stained 3D Fluorescent Cells with Filopodial Protrusions using Convolutional Neural Networks

of a convolutional neural network (CNN) designed for the segmentation of actin-stained cells in 3D+t confocal microscopy image data. The segmentation performance of the CNN structures. We show that the

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

  • 2018
  • D
  • Link
  • 1 - 10 out of 43 144