A Fast C++ Implementation of Neural Network Backpropagation Training Algorithm: Application to Bayesian Optimal Image Demosaicing
Yi-Qing Wang, Nicolas Limare
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