A Fast C++ Implementation of Neural Network Backpropagation Training Algorithm: Application to Bayesian Optimal Image Demosaicing
Yi-Qing Wang, Nicolas Limare
→ BibTeX
@article{ipol.2015.137,
    title   = {{A Fast C++ Implementation of Neural Network Backpropagation Training Algorithm: Application to Bayesian Optimal Image Demosaicing}},
    author  = {Wang, Yi-Qing and Limare, Nicolas},
    journal = {{Image Processing On Line}},
    volume  = {5},
    pages   = {257--266},
    year    = {2015},
    doi     = {10.5201/ipol.2015.137},
}
% if your bibliography style doesn't support doi fields:
    note    = {\url{https://doi.org/10.5201/ipol.2015.137}}
published
2015-09-16
reference
Yi-Qing Wang, and Nicolas Limare, A Fast C++ Implementation of Neural Network Backpropagation Training Algorithm: Application to Bayesian Optimal Image Demosaicing, Image Processing On Line, 5 (2015), pp. 257–266. https://doi.org/10.5201/ipol.2015.137

Communicated by José Lezama
Demo edited by Yi-Qing Wang

Abstract

Recent years have seen a surge of interest in multilayer neural networks fueled by their successful applications in numerous image processing and computer vision tasks. In this article, we describe a C++ implementation of the stochastic gradient descent to train a multilayer neural network, where a fast and accurate acceleration of tanh(·) is achieved with linear interpolation. As an example of application, we present a neural network able to deliver state-of-the-art performance in image demosaicing.

Download