Building recognition system based on deep learning

Deep learning architectures based on convolutional neural networks (CNN) are very successful in image recognition tasks. These architectures use a cascade of convolution layers and activation functions. The setup of the number of layers and the number of neurons in each layer, the choice of activati...

Full description

Saved in:
Bibliographic Details
Published in2016 Third International Conference on Artificial Intelligence and Pattern Recognition (AIPR) pp. 1 - 5
Main Author Bezak, Pavol
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.09.2016
Subjects
Biological neural networks
Buildings
convolutional neural networks
Data models
deep learning
Image recognition
Machine learning
Training
Online AccessGet full text
DOI10.1109/ICAIPR.2016.7585230

Cover

More Information
Summary:Deep learning architectures based on convolutional neural networks (CNN) are very successful in image recognition tasks. These architectures use a cascade of convolution layers and activation functions. The setup of the number of layers and the number of neurons in each layer, the choice of activation functions and training optimization algorithm are very important. I present GPU implementation of CNN with feature extractors designed for building recognition, learned in a supervised way and achieve very good results.
DOI:10.1109/ICAIPR.2016.7585230